{ "schema_version": "1.1", "instrument": { "figures_read_from": "cite-cut prose (gates.prose_of) since 2026-09-09", "warm_arm_walk": "per page, one warm immediately before that page's own questions, since 2026-09-09", "not_comparable_with": "reports whose schema_version is 1.0" }, "run_utc": "2026-09-13T03:50:16Z", "arm": "cold", "concurrency": 1, "effective_concurrency": 1, "seat": { "url_host_withheld": true, "model": "gemma-4-26b-a4b-fp8", "class": "gemma-class", "seed": "no --seed flag sent" }, "packnorm_definition_recorded_not_governing": "v3", "bank": { "path": "bank.json", "counts": { "on_page": 41, "off_page": 21, "total": 62 } }, "results": { "on_page_total": 41, "on_page_answered": 41, "on_page_partial": 0, "off_page_partial": 0, "sentences_kept": 138, "sentences_written": 140, "non_verbatim_figures": 0, "uncited": 0, "off_page_total": 21, "off_page_abstained": 21, "off_page_abstained_by_gate": 2, "off_page_abstained_by_model": 19, "off_page_flagged_but_not_verbatim": [], "on_page_abstained": 0, "off_page_cited": 19, "redaction_hits": 0, "cite_overlap_p50": 0.667, "cite_overlap_min": 0.0, "cite_overlap_max": 1.0, "cite_overlap_rows": 60, "seat_errors": 0, "p50_seconds": 1.065, "p95_seconds": 7.633, "pages_warmed": null, "cache_hits": null, "cache_hit_of": null }, "rows": [ { "slug": "three-new-voices-at-the-narrators-chair", "q": "what did the round cost in total, and how were the three new voices judged?", "ok": true, "answer": "The round's metered total came to $0.7652 § {#the-bill}. The three new voices were judged by a panel of seven seats from outside model families, six of which carried this round, reading lettered replies blind with no model names on them § {#seven-seats-six-carried-and-where-their-zeros-sit}. The article notes that the panel's reading is a measurement and that the counts in the ledger are the only figures provided § {#who's-at-the-chair-tonight}.", "served": "The round's metered total came to $0.7652 § {#the-bill}. The three new voices were judged by a panel of seven seats from outside model families, six of which carried this round, reading lettered replies blind with no model names on them § {#seven-seats-six-carried-and-where-their-zeros-sit}. The article notes that the panel's reading is a measurement and that the counts in the ledger are the only figures provided § {#who's-at-the-chair-tonight}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 11.13433836796321, "ttft_ms": 9734, "tokens_in": 82794, "tokens_out": 117, "cached_tokens": 32, "cites": [ "the-bill", "seven-seats-six-carried-and-where-their-zeros-sit", "whos-at-the-chair-tonight" ], "gates": { "cites": [ "the-bill", "seven-seats-six-carried-and-where-their-zeros-sit", "whos-at-the-chair-tonight" ], "cites_dropped": [], "cites_resolved": [ "whos-at-the-chair-tonight" ], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "0.7652" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-bill", "overlap": 0.8 }, { "i": 1, "cite": "seven-seats-six-carried-and-where-their-zeros-sit", "overlap": 0.684 }, { "i": 2, "cite": "whos-at-the-chair-tonight", "overlap": 0.444 } ], "cite_overlap_p50": 0.684, "id": "on-01", "kind": "on-page" }, { "slug": "two-new-frontier-models-at-the-rules-desk", "q": "how many cases did the blind head-to-head use, and did it separate the two models?", "ok": true, "answer": "The blind head-to-head used 36 cases and did not separate the two models § {#head-to-head}. A cluster bootstrap over the 36 cases puts the pooled preference rate for Claude Fable 5.1 at [0.444, 0.638], an interval that covers 0.5 § {#head-to-head}. The article notes that the narrator's chair job was moved out of this round before pre-registration was written § {#who-judged-and-who-wrote-this}.", "served": "The blind head-to-head used 36 cases and did not separate the two models § {#head-to-head}. A cluster bootstrap over the 36 cases puts the pooled preference rate for Claude Fable 5.1 at [0.444, 0.638], an interval that covers 0.5 § {#head-to-head}. The article notes that the narrator's chair job was moved out of this round before pre-registration was written § {#who-judged-and-who-wrote-this}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 2.7144724010140635, "ttft_ms": 1784, "tokens_in": 26913, "tokens_out": 118, "cached_tokens": 0, "cites": [ "head-to-head", "who-judged-and-who-wrote-this" ], "gates": { "cites": [ "head-to-head", "who-judged-and-who-wrote-this" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "36", "36", "5.1", "0.444", "0.638", "0.5" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "head-to-head", "overlap": 0.875 }, { "i": 1, "cite": "head-to-head", "overlap": 1.0 }, { "i": 2, "cite": "who-judged-and-who-wrote-this", "overlap": 0.5 } ], "cite_overlap_p50": 0.875, "id": "on-02", "kind": "on-page" }, { "slug": "six-worlds-painted-large", "q": "how many worlds were painted, and at what size and step count?", "ok": true, "answer": "Six worlds were painted at 2048×1280 and 40 steps § {#for-the-technically-curious}. The article does not mention any figures that were left out, moved, or not measured § {#for-the-technically-curious}.", "served": "Six worlds were painted at 2048×1280 and 40 steps § {#for-the-technically-curious}. The article does not mention any figures that were left out, moved, or not measured § {#for-the-technically-curious}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.5827346839942038, "ttft_ms": 258, "tokens_in": 3145, "tokens_out": 62, "cached_tokens": 32, "cites": [ "for-the-technically-curious" ], "gates": { "cites": [ "for-the-technically-curious" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "1280", "40" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "for-the-technically-curious", "overlap": 0.857 }, { "i": 1, "cite": "for-the-technically-curious", "overlap": 0.0 } ], "cite_overlap_p50": 0.428, "id": "on-03", "kind": "on-page" }, { "slug": "the-beat-lab-asked-and-answered", "q": "how many answers does the page carry, and does any model run to make it?", "ok": true, "answer": "The page carries twenty-seven answers and no model is asked for any answer on this page § {#where-these-answers-come-from}. The answers were drafted by AI agents in the byline but were read and approved word by word by humans § {#who-ran-this-and-thanks}.", "served": "The page carries twenty-seven answers and no model is asked for any answer on this page § {#where-these-answers-come-from}. The answers were drafted by AI agents in the byline but were read and approved word by word by humans § {#who-ran-this-and-thanks}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.681537483993452, "ttft_ms": 306, "tokens_in": 4643, "tokens_out": 64, "cached_tokens": 32, "cites": [ "where-these-answers-come-from", "who-ran-this-and-thanks" ], "gates": { "cites": [ "where-these-answers-come-from", "who-ran-this-and-thanks" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "where-these-answers-come-from", "overlap": 1.0 }, { "i": 1, "cite": "who-ran-this-and-thanks", "overlap": 1.0 } ], "cite_overlap_p50": 1.0, "id": "on-04", "kind": "on-page" }, { "slug": "ten-minutes-with-living-artists", "q": "how many tracks and releases went into the adapter, and what did the one listener prefer?", "ok": true, "answer": "The adapter was trained on 159 tracks from 41 releases § {#forty-one-releases-licence-by-licence}. The one listener preferred the untouched model, both times § {#the-ear}. The article notes that it did not measure whether an unlevelled corpus taught the adapter a level rather than a style § {#what-we-did-not-measure}.", "served": "The adapter was trained on 159 tracks from 41 releases § {#forty-one-releases-licence-by-licence}. The one listener preferred the untouched model, both times § {#the-ear}. The article notes that it did not measure whether an unlevelled corpus taught the adapter a level rather than a style § {#what-we-did-not-measure}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.329859181016218, "ttft_ms": 779, "tokens_in": 13206, "tokens_out": 84, "cached_tokens": 32, "cites": [ "forty-one-releases-licence-by-licence", "the-ear", "what-we-did-not-measure" ], "gates": { "cites": [ "forty-one-releases-licence-by-licence", "the-ear", "what-we-did-not-measure" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "159", "41" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "forty-one-releases-licence-by-licence", "overlap": 1.0 }, { "i": 1, "cite": "the-ear", "overlap": 0.714 }, { "i": 2, "cite": "what-we-did-not-measure", "overlap": 0.8 } ], "cite_overlap_p50": 0.8, "id": "on-05", "kind": "on-page" }, { "slug": "listen-for-yourself", "q": "how many renders are on the page, and what was done to their loudness?", "ok": true, "answer": "There are sixty-three players on the page, each playing a listening master of a raw render § {#how-to-listen}. The listening masters were created by applying one constant gain and nothing else, such as no limiter, no compression, no equalisation, or no trimming § {#how-to-listen}. The gain applied was the smaller of two numbers: how far the clip sits from −16 LUFS and how far its true peak sits from a −1 dBTP ceiling § {#how-to-listen}. Note that the raw renders themselves were never re-encoded, never trimmed, and never levelled after the fact § {#how-to-listen}.", "served": "There are sixty-three players on the page, each playing a listening master of a raw render § {#how-to-listen}. The listening masters were created by applying one constant gain and nothing else, such as no limiter, no compression, no equalisation, or no trimming § {#how-to-listen}. The gain applied was the smaller of two numbers: how far the clip sits from −16 LUFS and how far its true peak sits from a −1 dBTP ceiling § {#how-to-listen}. Note that the raw renders themselves were never re-encoded, never trimmed, and never levelled after the fact § {#how-to-listen}.", "partial": false, "sentences_kept": 4, "sentences_written": 4, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.6693353070295416, "ttft_ms": 839, "tokens_in": 14463, "tokens_out": 137, "cached_tokens": 32, "cites": [ "how-to-listen" ], "gates": { "cites": [ "how-to-listen" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "16" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "how-to-listen", "overlap": 1.0 }, { "i": 1, "cite": "how-to-listen", "overlap": 0.714 }, { "i": 2, "cite": "how-to-listen", "overlap": 1.0 }, { "i": 3, "cite": "how-to-listen", "overlap": 0.8 } ], "cite_overlap_p50": 0.9, "id": "on-06", "kind": "on-page" }, { "slug": "half-an-hour-with-dead-composers", "q": "how long did the Sousa and Bach adapters take to train?", "ok": true, "answer": "The Sousa adapter took 14 minutes 36 seconds to train § {#sousa-a-hundred-and-six-marches}, while the Bach adapter took 8 minutes 23 seconds § {#bach-the-pianist-who-freed-her-own-recordings}. The article notes that the better-loss Sousa checkpoint was never applied to the shipped adapter § {#sousa-a-hundred-and-six-marches}, and it did not perform a formal, blinded listening test to see if any merge sounds like a blend of its parents § {#what-we-did-not-measure}.", "served": "The Sousa adapter took 14 minutes 36 seconds to train § {#sousa-a-hundred-and-six-marches}, while the Bach adapter took 8 minutes 23 seconds § {#bach-the-pianist-who-freed-her-own-recordings}. The article notes that the better-loss Sousa checkpoint was never applied to the shipped adapter § {#sousa-a-hundred-and-six-marches}, and it did not perform a formal, blinded listening test to see if any merge sounds like a blend of its parents § {#what-we-did-not-measure}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.0759450279874727, "ttft_ms": 355, "tokens_in": 5703, "tokens_out": 132, "cached_tokens": 32, "cites": [ "sousa-a-hundred-and-six-marches", "bach-the-pianist-who-freed-her-own-recordings", "what-we-did-not-measure" ], "gates": { "cites": [ "sousa-a-hundred-and-six-marches", "bach-the-pianist-who-freed-her-own-recordings", "what-we-did-not-measure" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "14", "36", "8", "23" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "sousa-a-hundred-and-six-marches", "overlap": 0.545 }, { "i": 0, "cite": "bach-the-pianist-who-freed-her-own-recordings", "overlap": 0.455 }, { "i": 1, "cite": "sousa-a-hundred-and-six-marches", "overlap": 0.3 }, { "i": 1, "cite": "what-we-did-not-measure", "overlap": 0.65 } ], "cite_overlap_p50": 0.5, "id": "on-07", "kind": "on-page" }, { "slug": "chopin-in-five-minutes", "q": "how many recordings were used, and how long did the training take by the trainer's clock?", "ok": true, "answer": "Nineteen recordings were used for training, and the process took 4 minutes 49 seconds by the trainer's own clock § {#five-minutes-of-training-honestly-accounted}. The article notes that five recordings were held back for a test that has not yet run § {#five-minutes-of-training-honestly-accounted}.", "served": "Nineteen recordings were used for training, and the process took 4 minutes 49 seconds by the trainer's own clock § {#five-minutes-of-training-honestly-accounted}. The article notes that five recordings were held back for a test that has not yet run § {#five-minutes-of-training-honestly-accounted}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.6791856180061586, "ttft_ms": 277, "tokens_in": 3843, "tokens_out": 76, "cached_tokens": 32, "cites": [ "five-minutes-of-training-honestly-accounted" ], "gates": { "cites": [ "five-minutes-of-training-honestly-accounted" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "4", "49" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "five-minutes-of-training-honestly-accounted", "overlap": 0.833 }, { "i": 1, "cite": "five-minutes-of-training-honestly-accounted", "overlap": 0.75 } ], "cite_overlap_p50": 0.791, "id": "on-08", "kind": "on-page" }, { "slug": "the-same-sixteen", "q": "what did glm-5.3-flash score on the tool bench, and what did the local models score?", "ok": true, "answer": "The glm-5.3-flash reference arm scored 16/19 — 84.2%, Wilson 95% interval [62.4%, 94.5%] on the tool bench § {#sixteen-of-nineteen}. Two local models, gemma4:12b and qwen3.6:27b, also landed on the exact same count of 16/19 § {#two-local-models-sixteen-days-earlier}. The article notes that the judge exam, assistant exam, decode speed, and filing cabinet could not honestly be read on the cloud path § {#the-ledger-of-what-did-not-read}.", "served": "The glm-5.3-flash reference arm scored 16/19 — 84.2%, Wilson 95% interval [62.4%, 94.5%] on the tool bench § {#sixteen-of-nineteen}. Two local models, gemma4:12b and qwen3.6:27b, also landed on the exact same count of 16/19 § {#two-local-models-sixteen-days-earlier}. The article notes that the judge exam, assistant exam, decode speed, and filing cabinet could not honestly be read on the cloud path § {#the-ledger-of-what-did-not-read}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.2273626570240594, "ttft_ms": 386, "tokens_in": 6553, "tokens_out": 151, "cached_tokens": 32, "cites": [ "sixteen-of-nineteen", "two-local-models-sixteen-days-earlier", "the-ledger-of-what-did-not-read" ], "gates": { "cites": [ "sixteen-of-nineteen", "two-local-models-sixteen-days-earlier", "the-ledger-of-what-did-not-read" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "5.3", "16/19", "84.2", "95", "62.4", "94.5", "4:12", "3.6", "27", "16/19" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "sixteen-of-nineteen", "overlap": 0.846 }, { "i": 1, "cite": "two-local-models-sixteen-days-earlier", "overlap": 1.0 }, { "i": 2, "cite": "the-ledger-of-what-did-not-read", "overlap": 0.833 } ], "cite_overlap_p50": 0.846, "id": "on-09", "kind": "on-page" }, { "slug": "two-hours-on-battery", "q": "what speed did the mini pc hold on battery, and for how long?", "ok": true, "answer": "The mini PC held a speed of ~12 tokens/second on battery for about two hours § {#two-hours-at-12-tok-s-the-test-that-named-the-page}. The article notes that the GPU-server half of the test stayed unmeasured by design § {#two-hours-at-12-tok-s-the-test-that-named-the-page}.", "served": "The mini PC held a speed of ~12 tokens/second on battery for about two hours § {#two-hours-at-12-tok-s-the-test-that-named-the-page}. The article notes that the GPU-server half of the test stayed unmeasured by design § {#two-hours-at-12-tok-s-the-test-that-named-the-page}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.2231319620041177, "ttft_ms": 665, "tokens_in": 11094, "tokens_out": 91, "cached_tokens": 32, "cites": [ "two-hours-at-12-tok-s-the-test-that-named-the-page" ], "gates": { "cites": [ "two-hours-at-12-tok-s-the-test-that-named-the-page" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "12" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "two-hours-at-12-tok-s-the-test-that-named-the-page", "overlap": 1.0 }, { "i": 1, "cite": "two-hours-at-12-tok-s-the-test-that-named-the-page", "overlap": 0.714 } ], "cite_overlap_p50": 0.857, "id": "on-10", "kind": "on-page" }, { "slug": "the-instrument-travels", "q": "when the frozen exam moved to the smaller card, where did the ranked model land?", "ok": true, "answer": "The ranked model, qwen3.6:27b, cleared both judge floors and was ranked again § {#the-chair-and-who-gets-to-sit-in-it}. It achieved a kill-recall of 11 of 12 and a preservation of 8 of 9 § {#the-standings}. The article notes that the preservation delta was one item compared to the previous run, which remains under the two-item tie band § {#what-the-battery-was-for-the-instrument-travels}.", "served": "The ranked model, qwen3.6:27b, cleared both judge floors and was ranked again § {#the-chair-and-who-gets-to-sit-in-it}. It achieved a kill-recall of 11 of 12 and a preservation of 8 of 9 § {#the-standings}. The article notes that the preservation delta was one item compared to the previous run, which remains under the two-item tie band § {#what-the-battery-was-for-the-instrument-travels}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.1945159960305318, "ttft_ms": 503, "tokens_in": 8777, "tokens_out": 117, "cached_tokens": 32, "cites": [ "the-chair-and-who-gets-to-sit-in-it", "the-standings", "what-the-battery-was-for-the-instrument-travels" ], "gates": { "cites": [ "the-chair-and-who-gets-to-sit-in-it", "the-standings", "what-the-battery-was-for-the-instrument-travels" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "3.6", "27", "11", "12", "8", "9" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-chair-and-who-gets-to-sit-in-it", "overlap": 0.222 }, { "i": 1, "cite": "the-standings", "overlap": 0.8 }, { "i": 2, "cite": "what-the-battery-was-for-the-instrument-travels", "overlap": 0.615 } ], "cite_overlap_p50": 0.615, "id": "on-11", "kind": "on-page" }, { "slug": "nine-worlds-one-dog", "q": "what stays the same across the nine paintings?", "ok": true, "answer": "The founder's dog, who is a large black Portuguese Water Dog with one bright white chest patch, takes the same nap under the same tree in all nine painted worlds § {#top}. He maintains the same dog, same curl, and same tucked paws every time § {#for-the-technically-curious}.", "served": "The founder's dog, who is a large black Portuguese Water Dog with one bright white chest patch, takes the same nap under the same tree in all nine painted worlds § {#top}. He maintains the same dog, same curl, and same tucked paws every time § {#for-the-technically-curious}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.5144041560124606, "ttft_ms": 184, "tokens_in": 2058, "tokens_out": 66, "cached_tokens": 32, "cites": [ "top", "for-the-technically-curious" ], "gates": { "cites": [ "top", "for-the-technically-curious" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "top", "overlap": 0.526 }, { "i": 1, "cite": "for-the-technically-curious", "overlap": 0.444 } ], "cite_overlap_p50": 0.485, "id": "on-12", "kind": "on-page" }, { "slug": "what-150-watts-buys", "q": "what did the 450-watt cap cost the dense model, and what did it buy back?", "ok": true, "answer": "The 600 to 450 W cap cost the dense model 2.0% of throughput and bought back 138 W, 11 °C, and a 28% jump in efficiency § {#the-answer-in-one-paragraph}. At concurrency 16, the throughput moved from 94.6 to 92.7 tok/s per stream § {#the-answer-in-one-paragraph}. The article notes that it did not measure the cost of a long-context or prefill-heavy workload § {#what-this-page-does-not-say}.", "served": "The 600 to 450 W cap cost the dense model 2.0% of throughput and bought back 138 W, 11 °C, and a 28% jump in efficiency § {#the-answer-in-one-paragraph}. At concurrency 16, the throughput moved from 94.6 to 92.7 tok/s per stream § {#the-answer-in-one-paragraph}. The article notes that it did not measure the cost of a long-context or prefill-heavy workload § {#what-this-page-does-not-say}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.1710378699935973, "ttft_ms": 420, "tokens_in": 7269, "tokens_out": 133, "cached_tokens": 32, "cites": [ "the-answer-in-one-paragraph", "what-this-page-does-not-say" ], "gates": { "cites": [ "the-answer-in-one-paragraph", "what-this-page-does-not-say" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "600", "450", "2.0", "138", "11", "28", "16", "94.6", "92.7" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-answer-in-one-paragraph", "overlap": 0.8 }, { "i": 1, "cite": "the-answer-in-one-paragraph", "overlap": 1.0 }, { "i": 2, "cite": "what-this-page-does-not-say", "overlap": 0.667 } ], "cite_overlap_p50": 0.8, "id": "on-13", "kind": "on-page" }, { "slug": "how-the-beat-lab-works", "q": "where is the sound made, and how long does a typical wish take?", "ok": true, "answer": "Every sound in the Beat Lab is synthesised by the user's own browser § {#the-sound-is-made-on-your-device}. A typical wish takes about 4 s § {#what-happens-when-you-ask-the-genie}. The article does not mention what was left out, moved, or not measured in relation to these specific details.", "served": "Every sound in the Beat Lab is synthesised by the user's own browser § {#the-sound-is-made-on-your-device}. A typical wish takes about 4 s § {#what-happens-when-you-ask-the-genie}. The article does not mention what was left out, moved, or not measured in relation to these specific details.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 2.955599633976817, "ttft_ms": 2224, "tokens_in": 31469, "tokens_out": 81, "cached_tokens": 32, "cites": [ "the-sound-is-made-on-your-device", "what-happens-when-you-ask-the-genie" ], "gates": { "cites": [ "the-sound-is-made-on-your-device", "what-happens-when-you-ask-the-genie" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "4" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-sound-is-made-on-your-device", "overlap": 0.875 }, { "i": 1, "cite": "what-happens-when-you-ask-the-genie", "overlap": 1.0 } ], "cite_overlap_p50": 0.938, "id": "on-14", "kind": "on-page" }, { "slug": "the-typist-and-the-developer", "q": "how long did the developer take to develop one picture?", "ok": true, "answer": "The developer developed a picture in 1.54 seconds § {#the-developer}. When the typist was streaming tokens at the same time, the developer took 1.82 seconds per sketch § {#one-card-both-jobs-at-once}. The article does not mention how much traffic was present during the run § {#what-we-did-not-measure-said-out-loud}.", "served": "The developer developed a picture in 1.54 seconds § {#the-developer}. When the typist was streaming tokens at the same time, the developer took 1.82 seconds per sketch § {#one-card-both-jobs-at-once}. The article does not mention how much traffic was present during the run § {#what-we-did-not-measure-said-out-loud}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.8190374840050936, "ttft_ms": 341, "tokens_in": 5536, "tokens_out": 87, "cached_tokens": 32, "cites": [ "the-developer", "one-card-both-jobs-at-once", "what-we-did-not-measure-said-out-loud" ], "gates": { "cites": [ "the-developer", "one-card-both-jobs-at-once", "what-we-did-not-measure-said-out-loud" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "1.54", "1.82" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-developer", "overlap": 1.0 }, { "i": 1, "cite": "one-card-both-jobs-at-once", "overlap": 0.909 }, { "i": 2, "cite": "what-we-did-not-measure-said-out-loud", "overlap": 0.5 } ], "cite_overlap_p50": 0.909, "id": "on-15", "kind": "on-page" }, { "slug": "a-rig-your-friend-already-owns", "q": "how much faster was the workstation card than the 3090 on the game's own art?", "ok": true, "answer": "The 96 GB card was 3.4× faster than the RTX 3090 when running the FLUX.2 klein-4B model used for the game's sketches § {#the-table-that-answers-the-question}. Across all models, the 96 GB card's median render times ranged from 0.48 s to 7.84 s, while the 3090's times ranged from 1.65 s to 33.01 s § {#the-table-that-answers-the-question}. The article notes that the study did not test 8–12 GB cards § {#three-findings-we-didnt-order}.", "served": "The 96 GB card was 3.4× faster than the RTX 3090 when running the FLUX.2 klein-4B model used for the game's sketches § {#the-table-that-answers-the-question}. Across all models, the 96 GB card's median render times ranged from 0.48 s to 7.84 s, while the 3090's times ranged from 1.65 s to 33.01 s § {#the-table-that-answers-the-question}. The article notes that the study did not test 8–12 GB cards § {#three-findings-we-didnt-order}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.1335061360150576, "ttft_ms": 311, "tokens_in": 4777, "tokens_out": 155, "cached_tokens": 32, "cites": [ "the-table-that-answers-the-question", "three-findings-we-didnt-order" ], "gates": { "cites": [ "the-table-that-answers-the-question", "three-findings-we-didnt-order" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "96", "3.4", "3090", "2", "4", "96", "0.48", "7.84", "3090", "1.65", "33.01", "8-12" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-table-that-answers-the-question", "overlap": 0.5 }, { "i": 1, "cite": "the-table-that-answers-the-question", "overlap": 0.467 }, { "i": 2, "cite": "three-findings-we-didnt-order", "overlap": 0.667 } ], "cite_overlap_p50": 0.5, "id": "on-16", "kind": "on-page" }, { "slug": "how-a-vision-model-sees", "q": "how many tokens does an 896 px picture become, and how long does its prefill take?", "ok": true, "answer": "An 896 px picture becomes 199 tokens and its prefill takes 184 ms § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}. This measurement was recorded on the seat the cove ships, which is minicpm-v4.5 § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}. The article does not mention the token cost or prefill time for the resident seat at this resolution § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}.", "served": "An 896 px picture becomes 199 tokens and its prefill takes 184 ms § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}. This measurement was recorded on the seat the cove ships, which is minicpm-v4.5 § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}. The article does not mention the token cost or prefill time for the resident seat at this resolution § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.566284161992371, "ttft_ms": 630, "tokens_in": 10311, "tokens_out": 154, "cached_tokens": 32, "cites": [ "finding-one-a-picture-is-199-tokens-at-896-px-and-the" ], "gates": { "cites": [ "finding-one-a-picture-is-199-tokens-at-896-px-and-the" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "896", "199", "184", "4.5" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "finding-one-a-picture-is-199-tokens-at-896-px-and-the", "overlap": 0.8 }, { "i": 1, "cite": "finding-one-a-picture-is-199-tokens-at-896-px-and-the", "overlap": 0.667 }, { "i": 2, "cite": "finding-one-a-picture-is-199-tokens-at-896-px-and-the", "overlap": 0.75 } ], "cite_overlap_p50": 0.75, "id": "on-17", "kind": "on-page" }, { "slug": "fifty-seven-milliseconds", "q": "which painter is the fastest cell, and at what time?", "ok": true, "answer": "The distilled painter is the fastest cell in the second run, recording a time of 0.62 s at 4 steps § {#finding-four-the-argument-with-our-own-settings-and-what-it}. The article notes that the published pages serve compressed derivatives rather than the lossless masters used for the calculations § {#how-to-check-our-work-and-see-it-live}.", "served": "The distilled painter is the fastest cell in the second run, recording a time of 0.62 s at 4 steps § {#finding-four-the-argument-with-our-own-settings-and-what-it}. The article notes that the published pages serve compressed derivatives rather than the lossless masters used for the calculations § {#how-to-check-our-work-and-see-it-live}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.8334511750144884, "ttft_ms": 343, "tokens_in": 5434, "tokens_out": 90, "cached_tokens": 32, "cites": [ "finding-four-the-argument-with-our-own-settings-and-what-it", "how-to-check-our-work-and-see-it-live" ], "gates": { "cites": [ "finding-four-the-argument-with-our-own-settings-and-what-it", "how-to-check-our-work-and-see-it-live" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "0.62", "4" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "finding-four-the-argument-with-our-own-settings-and-what-it", "overlap": 0.9 }, { "i": 1, "cite": "how-to-check-our-work-and-see-it-live", "overlap": 0.636 } ], "cite_overlap_p50": 0.768, "id": "on-18", "kind": "on-page" }, { "slug": "the-dog-the-dice-and-the-painter", "q": "how big is the file the whole world is written in?", "ok": true, "answer": "The world is written in a single YAML file consisting of 16,705 lines § {#the-world-is-a-file}. This file contains six regions, forty NPCs, fifty-nine quests, and three kinds of adoptable pet § {#the-world-is-a-file}. No scores or instrumentation were used for this specific walk § {#the-walk-is-a-walk}.", "served": "The world is written in a single YAML file consisting of 16,705 lines § {#the-world-is-a-file}. This file contains six regions, forty NPCs, fifty-nine quests, and three kinds of adoptable pet § {#the-world-is-a-file}. No scores or instrumentation were used for this specific walk § {#the-walk-is-a-walk}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.880868164007552, "ttft_ms": 370, "tokens_in": 6116, "tokens_out": 87, "cached_tokens": 32, "cites": [ "the-world-is-a-file" ], "gates": { "cites": [ "the-world-is-a-file" ], "cites_dropped": [ "the-walk-is-a-walk" ], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [ "cite: 1 cite(s) not in this page's anchors: the-walk-is-a-walk" ], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [ "the-walk-is-a-walk" ] }, "figures": [ "16,705" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-world-is-a-file", "overlap": 0.778 }, { "i": 1, "cite": "the-world-is-a-file", "overlap": 0.917 } ], "cite_overlap_p50": 0.848, "id": "on-19", "kind": "on-page" }, { "slug": "where-new-knowledge-comes-from", "q": "what are the two engines the page names for where new knowledge comes from?", "ok": true, "answer": "The two engines named are present in the data, unmined, and implied by the rules, unvisited § {#two-kinds-of-there-all-along}. The first engine involves reading patterns that were already in archives, such as co-evolution fingerprints or molecular shapes that kill bacteria § {#the-first-engine-the-archive-nobody-had-read}. The second engine involves walking regions of rule-space that no row of data contains, such as a planet's position in 1631 or an anti-electron § {#the-second-engine-the-rooms-the-rules-imply}. Structural biologists noted that these engines left out how proteins pair up, how they move, and what one mutation does § {#the-first-engine-the-archive-nobody-had-read}.", "served": "The two engines named are present in the data, unmined, and implied by the rules, unvisited § {#two-kinds-of-there-all-along}. The first engine involves reading patterns that were already in archives, such as co-evolution fingerprints or molecular shapes that kill bacteria § {#the-first-engine-the-archive-nobody-had-read}. The second engine involves walking regions of rule-space that no row of data contains, such as a planet's position in 1631 or an anti-electron § {#the-second-engine-the-rooms-the-rules-imply}. Structural biologists noted that these engines left out how proteins pair up, how they move, and what one mutation does § {#the-first-engine-the-archive-nobody-had-read}.", "partial": false, "sentences_kept": 4, "sentences_written": 4, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.2822839530417696, "ttft_ms": 348, "tokens_in": 5472, "tokens_out": 173, "cached_tokens": 32, "cites": [ "two-kinds-of-there-all-along", "the-first-engine-the-archive-nobody-had-read", "the-second-engine-the-rooms-the-rules-imply" ], "gates": { "cites": [ "two-kinds-of-there-all-along", "the-first-engine-the-archive-nobody-had-read", "the-second-engine-the-rooms-the-rules-imply" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "1631" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "two-kinds-of-there-all-along", "overlap": 0.889 }, { "i": 1, "cite": "the-first-engine-the-archive-nobody-had-read", "overlap": 0.357 }, { "i": 2, "cite": "the-second-engine-the-rooms-the-rules-imply", "overlap": 0.429 }, { "i": 3, "cite": "the-first-engine-the-archive-nobody-had-read", "overlap": 0.231 } ], "cite_overlap_p50": 0.393, "id": "on-20", "kind": "on-page" }, { "slug": "compression-is-the-objective", "q": "what does the page say a language model is, and what prize does it point to?", "ok": true, "answer": "A language model is a compression of its corpus § {#the-punchline}. The article points to the Hutter Prize, which charges for everything including self-extracting entries and every decompressor byte counted § {#the-punchline}. The text notes that a frontier model cannot even enter this prize because the weights outweigh the file by more than a hundred times § {#the-punchline}.", "served": "A language model is a compression of its corpus § {#the-punchline}. The article points to the Hutter Prize, which charges for everything including self-extracting entries and every decompressor byte counted § {#the-punchline}. The text notes that a frontier model cannot even enter this prize because the weights outweigh the file by more than a hundred times § {#the-punchline}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.8018135459860787, "ttft_ms": 344, "tokens_in": 5448, "tokens_out": 81, "cached_tokens": 32, "cites": [ "the-punchline" ], "gates": { "cites": [ "the-punchline" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-punchline", "overlap": 1.0 }, { "i": 1, "cite": "the-punchline", "overlap": 0.333 }, { "i": 2, "cite": "the-punchline", "overlap": 0.467 } ], "cite_overlap_p50": 0.467, "id": "on-21", "kind": "on-page" }, { "slug": "the-free-speed-wasnt-free", "q": "what was the production median before the change, and what caused the speed-up?", "ok": true, "answer": "The production median was 138.6 tok/s over 1,982 live rulings § {#the-day-the-box-got-faster}. The speed-up was caused by an ollama commit that changed the default repeat_penalty from 1.1 to 1.0, which removed a penalties stage that had been running on every token § {#the-two-line-commit}. The article notes that the quality half of this change remains unmeasured § {#the-part-that-isnt-about-speed}.", "served": "The production median was 138.6 tok/s over 1,982 live rulings § {#the-day-the-box-got-faster}. The speed-up was caused by an ollama commit that changed the default repeat_penalty from 1.1 to 1.0, which removed a penalties stage that had been running on every token § {#the-two-line-commit}. The article notes that the quality half of this change remains unmeasured § {#the-part-that-isnt-about-speed}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.0989709999994375, "ttft_ms": 436, "tokens_in": 7529, "tokens_out": 116, "cached_tokens": 32, "cites": [ "the-day-the-box-got-faster", "the-two-line-commit", "the-part-that-isnt-about-speed" ], "gates": { "cites": [ "the-day-the-box-got-faster", "the-two-line-commit", "the-part-that-isnt-about-speed" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "138.6", "1,982", "1.1", "1.0" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-day-the-box-got-faster", "overlap": 1.0 }, { "i": 1, "cite": "the-two-line-commit", "overlap": 0.625 }, { "i": 2, "cite": "the-part-that-isnt-about-speed", "overlap": 0.667 } ], "cite_overlap_p50": 0.667, "id": "on-22", "kind": "on-page" }, { "slug": "the-compressed-photograph", "q": "how much slower was the uncompressed original than the compressed build?", "ok": true, "answer": "The uncompressed original was 3.4× slower than the trained-4-bit build § {#the-same-question-down-the-whole-ladder}. The uncompressed original's speed was 58.1 tok/s compared to the trained-4-bit build's 134.4 tok/s § {#the-same-question-down-the-whole-ladder}. The article does not measure perplexity § {#what-this-page-does-not-say}.", "served": "The uncompressed original was 3.4× slower than the trained-4-bit build § {#the-same-question-down-the-whole-ladder}. The uncompressed original's speed was 58.1 tok/s compared to the trained-4-bit build's 134.4 tok/s § {#the-same-question-down-the-whole-ladder}. The article does not measure perplexity § {#what-this-page-does-not-say}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.1480291099869646, "ttft_ms": 500, "tokens_in": 8637, "tokens_out": 109, "cached_tokens": 32, "cites": [ "the-same-question-down-the-whole-ladder", "what-this-page-does-not-say" ], "gates": { "cites": [ "the-same-question-down-the-whole-ladder", "what-this-page-does-not-say" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "3.4", "4", "58.1", "4", "134.4" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-same-question-down-the-whole-ladder", "overlap": 0.833 }, { "i": 1, "cite": "the-same-question-down-the-whole-ladder", "overlap": 0.889 }, { "i": 2, "cite": "what-this-page-does-not-say", "overlap": 1.0 } ], "cite_overlap_p50": 0.889, "id": "on-23", "kind": "on-page" }, { "slug": "three-at-the-table", "q": "what is the true active share for the live seat, and what does the page call the two numbers in a model name?", "ok": true, "answer": "The true active share for the live seat is 14.4% of the model's bytes § {#the-payroll-and-the-meeting}. The two numbers in a model name are called the payroll and the meeting § {#the-tag-with-two-numbers}. The article notes that it does not measure the latency trade-off of streaming experts from system RAM § {#the-part-nobody-warns-you-about-the-whole-payroll-needs-an}.", "served": "The true active share for the live seat is 14.4% of the model's bytes § {#the-payroll-and-the-meeting}. The two numbers in a model name are called the payroll and the meeting § {#the-tag-with-two-numbers}. The article notes that it does not measure the latency trade-off of streaming experts from system RAM § {#the-part-nobody-warns-you-about-the-whole-payroll-needs-an}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.0547421939554624, "ttft_ms": 449, "tokens_in": 7685, "tokens_out": 104, "cached_tokens": 32, "cites": [ "the-payroll-and-the-meeting", "the-tag-with-two-numbers", "the-part-nobody-warns-you-about-the-whole-payroll-needs-an" ], "gates": { "cites": [ "the-payroll-and-the-meeting", "the-tag-with-two-numbers", "the-part-nobody-warns-you-about-the-whole-payroll-needs-an" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "14.4" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-payroll-and-the-meeting", "overlap": 1.0 }, { "i": 1, "cite": "the-tag-with-two-numbers", "overlap": 0.714 }, { "i": 2, "cite": "the-part-nobody-warns-you-about-the-whole-payroll-needs-an", "overlap": 0.5 } ], "cite_overlap_p50": 0.714, "id": "on-24", "kind": "on-page" }, { "slug": "reading-is-fast", "q": "what was the median reading speed, and why is reading faster than writing?", "ok": true, "answer": "The median reading speed was 5,415 tokens/s § {#a-measurement-from-our-own-card}. Reading is faster because it is parallel, as the model can process all tokens in a prompt at the same time since the text already exists § {#reading-is-a-group-photo}. In contrast, writing is serial because the model must choose tokens one at a time as the future of the sentence does not yet exist § {#writing-is-one-at-a-time}.", "served": "The median reading speed was 5,415 tokens/s § {#a-measurement-from-our-own-card}. Reading is faster because it is parallel, as the model can process all tokens in a prompt at the same time since the text already exists § {#reading-is-a-group-photo}. In contrast, writing is serial because the model must choose tokens one at a time as the future of the sentence does not yet exist § {#writing-is-one-at-a-time}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.9463093590456992, "ttft_ms": 350, "tokens_in": 5557, "tokens_out": 108, "cached_tokens": 32, "cites": [ "a-measurement-from-our-own-card", "reading-is-a-group-photo", "writing-is-one-at-a-time" ], "gates": { "cites": [ "a-measurement-from-our-own-card", "reading-is-a-group-photo", "writing-is-one-at-a-time" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "5,415" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "a-measurement-from-our-own-card", "overlap": 1.0 }, { "i": 1, "cite": "reading-is-a-group-photo", "overlap": 0.643 }, { "i": 2, "cite": "writing-is-one-at-a-time", "overlap": 0.786 } ], "cite_overlap_p50": 0.786, "id": "on-25", "kind": "on-page" }, { "slug": "three-librarians", "q": "how many dimensions does the embedder's map have, and what does the third librarian do?", "ok": true, "answer": "The embedder's map has 768 directions § {#the-second-librarian-searches-by-meaning}. The third librarian works only within the user's chosen game aisle by picking up the edition's rulebook and any matched publisher errata § {#the-third-librarian-never-left-your-aisle}. The article does not mention what was left out, moved, or not measured in relation to these specific components § {#the-nerd-shelf-the-numbers-from-the-shipped-configuration}.", "served": "The embedder's map has 768 directions § {#the-second-librarian-searches-by-meaning}. The third librarian works only within the user's chosen game aisle by picking up the edition's rulebook and any matched publisher errata § {#the-third-librarian-never-left-your-aisle}. The article does not mention what was left out, moved, or not measured in relation to these specific components § {#the-nerd-shelf-the-numbers-from-the-shipped-configuration}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.0169110749848187, "ttft_ms": 364, "tokens_in": 5913, "tokens_out": 118, "cached_tokens": 32, "cites": [ "the-second-librarian-searches-by-meaning", "the-third-librarian-never-left-your-aisle", "the-nerd-shelf-the-numbers-from-the-shipped-configuration" ], "gates": { "cites": [ "the-second-librarian-searches-by-meaning", "the-third-librarian-never-left-your-aisle", "the-nerd-shelf-the-numbers-from-the-shipped-configuration" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "768" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-second-librarian-searches-by-meaning", "overlap": 0.75 }, { "i": 1, "cite": "the-third-librarian-never-left-your-aisle", "overlap": 0.688 }, { "i": 2, "cite": "the-nerd-shelf-the-numbers-from-the-shipped-configuration", "overlap": 0.0 } ], "cite_overlap_p50": 0.688, "id": "on-26", "kind": "on-page" }, { "slug": "the-new-kid", "q": "which seat did the new model pass, and which floor did it miss?", "ok": true, "answer": "The qwen3.8:27b model passed the classifier seat, clearing all five pre-registered gates § {#the-classifier-seat-five-gates-all-pass-faster}, but it failed the judge seat by missing the preservation floor of 13 with a result of 11 of 16 § {#the-judge-seat-and-the-floor-it-missed}. The article notes that the classifier seat's G1 result of 0/20 was based on 20 authored items rather than the approximately 40 intended by the pre-registration § {#the-classifier-seat-five-gates-all-pass-faster}.", "served": "The qwen3.8:27b model passed the classifier seat, clearing all five pre-registered gates § {#the-classifier-seat-five-gates-all-pass-faster}, but it failed the judge seat by missing the preservation floor of 13 with a result of 11 of 16 § {#the-judge-seat-and-the-floor-it-missed}. The article notes that the classifier seat's G1 result of 0/20 was based on 20 authored items rather than the approximately 40 intended by the pre-registration § {#the-classifier-seat-five-gates-all-pass-faster}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.8270219240221195, "ttft_ms": 895, "tokens_in": 15091, "tokens_out": 144, "cached_tokens": 32, "cites": [ "the-classifier-seat-five-gates-all-pass-faster", "the-judge-seat-and-the-floor-it-missed" ], "gates": { "cites": [ "the-classifier-seat-five-gates-all-pass-faster", "the-judge-seat-and-the-floor-it-missed" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "3.8", "27", "13", "11", "16", "0/20", "20", "40" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-classifier-seat-five-gates-all-pass-faster", "overlap": 0.579 }, { "i": 0, "cite": "the-judge-seat-and-the-floor-it-missed", "overlap": 0.684 }, { "i": 1, "cite": "the-classifier-seat-five-gates-all-pass-faster", "overlap": 0.667 } ], "cite_overlap_p50": 0.667, "id": "on-27", "kind": "on-page" }, { "slug": "llms-txt", "q": "did any ai crawler fetch the file in the first thirty days, and how big is the largest measured llms-full file?", "ok": true, "answer": "No AI crawler asked for the file in thirty days of logs § {#does-anyone-fetch-it}. The largest measured llms-full file weighs 30.7 MiB § {#where-the-file-came-from}. The article notes that the bench does not measure crawling, fetching, adoption, or agent behaviour in the wild § {#the-bench-if-the-map-arrives-does-it-help}.", "served": "No AI crawler asked for the file in thirty days of logs § {#does-anyone-fetch-it}. The largest measured llms-full file weighs 30.7 MiB § {#where-the-file-came-from}. The article notes that the bench does not measure crawling, fetching, adoption, or agent behaviour in the wild § {#the-bench-if-the-map-arrives-does-it-help}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.3550619350280613, "ttft_ms": 753, "tokens_in": 12541, "tokens_out": 93, "cached_tokens": 32, "cites": [ "does-anyone-fetch-it", "where-the-file-came-from", "the-bench-if-the-map-arrives-does-it-help" ], "gates": { "cites": [ "does-anyone-fetch-it", "where-the-file-came-from", "the-bench-if-the-map-arrives-does-it-help" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "30.7" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "does-anyone-fetch-it", "overlap": 0.571 }, { "i": 1, "cite": "where-the-file-came-from", "overlap": 1.0 }, { "i": 2, "cite": "the-bench-if-the-map-arrives-does-it-help", "overlap": 0.0 } ], "cite_overlap_p50": 0.571, "id": "on-28", "kind": "on-page" }, { "slug": "the-open-call", "q": "how many models were handed the frozen moment, and what did the round cost?", "ok": true, "answer": "Twenty language models were handed the same frozen moment § {#top}. The round's metered spend was $2.2826 § {#2-2826-over-56-metered-calls-against-38-49-of-caps}. The article notes that the agent transport holds no cost figure and no token counters § {#the-author-of-this-page-is-a-contestant-in-it}.", "served": "Twenty language models were handed the same frozen moment § {#top}. The round's metered spend was $2.2826 § {#2-2826-over-56-metered-calls-against-38-49-of-caps}. The article notes that the agent transport holds no cost figure and no token counters § {#the-author-of-this-page-is-a-contestant-in-it}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 7.6854497590102255, "ttft_ms": 6316, "tokens_in": 63492, "tokens_out": 98, "cached_tokens": 32, "cites": [ "top", "2-2826-over-56-metered-calls-against-38-49-of-caps", "the-author-of-this-page-is-a-contestant-in-it" ], "gates": { "cites": [ "top", "2-2826-over-56-metered-calls-against-38-49-of-caps", "the-author-of-this-page-is-a-contestant-in-it" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "2.2826" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "top", "overlap": 1.0 }, { "i": 1, "cite": "2-2826-over-56-metered-calls-against-38-49-of-caps", "overlap": 0.5 }, { "i": 2, "cite": "the-author-of-this-page-is-a-contestant-in-it", "overlap": 0.875 } ], "cite_overlap_p50": 0.875, "id": "on-29", "kind": "on-page" }, { "slug": "where-your-question-goes", "q": "how long does every notebook on the server keep its entries?", "ok": true, "answer": "Every notebook on the server now keeps thirty days of entries § {#the-first-promise-your-visit-stays-between-us}. This rule applies to the tour guide's notebook as well § {#the-first-promise-your-visit-stays-between-us}. A note mentions that the rules helper's own visit log had previously stopped writing a month earlier due to a configuration rewrite § {#the-first-promise-your-visit-stays-between-us}.", "served": "Every notebook on the server now keeps thirty days of entries § {#the-first-promise-your-visit-stays-between-us}. This rule applies to the tour guide's notebook as well § {#the-first-promise-your-visit-stays-between-us}. A note mentions that the rules helper's own visit log had previously stopped writing a month earlier due to a configuration rewrite § {#the-first-promise-your-visit-stays-between-us}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.872892705956474, "ttft_ms": 319, "tokens_in": 4985, "tokens_out": 102, "cached_tokens": 32, "cites": [ "the-first-promise-your-visit-stays-between-us" ], "gates": { "cites": [ "the-first-promise-your-visit-stays-between-us" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-first-promise-your-visit-stays-between-us", "overlap": 0.875 }, { "i": 1, "cite": "the-first-promise-your-visit-stays-between-us", "overlap": 0.833 }, { "i": 2, "cite": "the-first-promise-your-visit-stays-between-us", "overlap": 0.733 } ], "cite_overlap_p50": 0.833, "id": "on-30", "kind": "on-page" }, { "slug": "how-we-work", "q": "what does the page say about the humans and agents who make each exhibit?", "ok": true, "answer": "The page states that the human generates and judges while the agent amplifies and verifies § {#the-plain-english-version}. Agents perform tasks such as recon, planning, hardening, and drafting, whereas the human operator provides the initial spark, makes binding rulings, and provides the final sign-off for release § {#the-thorough-walk}. The human makes the work true by deciding what is worth testing and what the numbers mean, while agents make the work bigger by testing more models and verifying more claims § {#the-thorough-walk}. Regarding what was not measured, the voice trial's original five questions were never persisted, so it ran a rebuilt probe on a scale of its own that compares to nothing outside it § {#the-plain-english-version}.", "served": "The page states that the human generates and judges while the agent amplifies and verifies § {#the-plain-english-version}. Agents perform tasks such as recon, planning, hardening, and drafting, whereas the human operator provides the initial spark, makes binding rulings, and provides the final sign-off for release § {#the-thorough-walk}. The human makes the work true by deciding what is worth testing and what the numbers mean, while agents make the work bigger by testing more models and verifying more claims § {#the-thorough-walk}. Regarding what was not measured, the voice trial's original five questions were never persisted, so it ran a rebuilt probe on a scale of its own that compares to nothing outside it § {#the-plain-english-version}.", "partial": false, "sentences_kept": 4, "sentences_written": 4, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.1862402890110388, "ttft_ms": 328, "tokens_in": 5210, "tokens_out": 159, "cached_tokens": 32, "cites": [ "the-plain-english-version", "the-thorough-walk" ], "gates": { "cites": [ "the-plain-english-version", "the-thorough-walk" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-plain-english-version", "overlap": 0.375 }, { "i": 1, "cite": "the-thorough-walk", "overlap": 0.55 }, { "i": 2, "cite": "the-thorough-walk", "overlap": 0.824 }, { "i": 3, "cite": "the-plain-english-version", "overlap": 0.824 } ], "cite_overlap_p50": 0.687, "id": "on-31", "kind": "on-page" }, { "slug": "the-move", "q": "what did the median search time go from and to after the move?", "ok": true, "answer": "The median search time went from 242.0 ms in the laptop era to 77.5 ms in the new era § {#receipts}. This comparison is noted as the retrieval leg that the move actually touched § {#receipts}.", "served": "The median search time went from 242.0 ms in the laptop era to 77.5 ms in the new era § {#receipts}. This comparison is noted as the retrieval leg that the move actually touched § {#receipts}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.6868988790083677, "ttft_ms": 370, "tokens_in": 6101, "tokens_out": 52, "cached_tokens": 32, "cites": [ "receipts" ], "gates": { "cites": [ "receipts" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "242.0", "77.5" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "receipts", "overlap": 0.9 }, { "i": 1, "cite": "receipts", "overlap": 0.857 } ], "cite_overlap_p50": 0.879, "id": "on-32", "kind": "on-page" }, { "slug": "chair-trials", "q": "how many models and arms sat the five exams, and did the box stop serving?", "ok": true, "answer": "Nine models and eleven arms sat the five exams, and the box stayed in service throughout § {#top}. The article notes that the roster registers no on-disk blob size because no leg of this arc measured one § {#roster}.", "served": "Nine models and eleven arms sat the five exams, and the box stayed in service throughout § {#top}. The article notes that the roster registers no on-disk blob size because no leg of this arc measured one § {#roster}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 2.563001703005284, "ttft_ms": 2113, "tokens_in": 30322, "tokens_out": 48, "cached_tokens": 32, "cites": [ "top", "roster" ], "gates": { "cites": [ "top", "roster" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "top", "overlap": 1.0 }, { "i": 1, "cite": "roster", "overlap": 1.0 } ], "cite_overlap_p50": 1.0, "id": "on-33", "kind": "on-page" }, { "slug": "cove-voice-head-to-head", "q": "what happened to the August class's best voice at the cove's gate?", "ok": true, "answer": "The August class's best voice, qwen3.6:27b, was refused at the gate § {#the-verdict}. This candidate was rejected because it invented facts twice in thirteen prompts, specifically failing the canon floor § {#the-verdict} and the latency floor § {#floor-4-latency}. The article notes that no seat proposal, live flip, deployment change, or threshold table was issued as a result of this trial § {#the-verdict}.", "served": "The August class's best voice, qwen3.6:27b, was refused at the gate § {#the-verdict}. This candidate was rejected because it invented facts twice in thirteen prompts, specifically failing the canon floor § {#the-verdict} and the latency floor § {#floor-4-latency}. The article notes that no seat proposal, live flip, deployment change, or threshold table was issued as a result of this trial § {#the-verdict}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.700047229998745, "ttft_ms": 1001, "tokens_in": 16668, "tokens_out": 100, "cached_tokens": 32, "cites": [ "the-verdict", "floor-4-latency" ], "gates": { "cites": [ "the-verdict", "floor-4-latency" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "3.6", "27" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-verdict", "overlap": 0.375 }, { "i": 1, "cite": "the-verdict", "overlap": 0.769 }, { "i": 1, "cite": "floor-4-latency", "overlap": 0.308 }, { "i": 2, "cite": "the-verdict", "overlap": 0.667 } ], "cite_overlap_p50": 0.521, "id": "on-34", "kind": "on-page" }, { "slug": "outside-judges", "q": "how many outside labs re-judged, and what was the widest cross-vendor gap?", "ok": true, "answer": "Four rival frontier labs re-judged the sealed rounds § {#vendors}. The widest cross-vendor gap on any arm was 0.178 § {#vendors}. This gap occurred on muse-glimmer:30b-q8_0-dflash, where mistral read it at 0.450 against nvidia at 0.628 § {#vendors}.", "served": "Four rival frontier labs re-judged the sealed rounds § {#vendors}. The widest cross-vendor gap on any arm was 0.178 § {#vendors}. This gap occurred on muse-glimmer:30b-q8_0-dflash, where mistral read it at 0.450 against nvidia at 0.628 § {#vendors}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.1509207990020514, "ttft_ms": 633, "tokens_in": 10362, "tokens_out": 82, "cached_tokens": 32, "cites": [ "vendors" ], "gates": { "cites": [ "vendors" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "0.178", "30", "80", "0.450", "0.628" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "vendors", "overlap": 0.429 }, { "i": 1, "cite": "vendors", "overlap": 1.0 }, { "i": 2, "cite": "vendors", "overlap": 0.909 } ], "cite_overlap_p50": 0.909, "id": "on-35", "kind": "on-page" }, { "slug": "august-arrivals", "q": "how many models landed that week, and what share broke the response contract?", "ok": true, "answer": "Four open-weight models landed in one week of August 2026 § {#top}. All four of these models broke the response contract on more than 10% of calls § {#exam-one-the-judge-chair}. The article notes that olmo-3.1:32b-think-q4_K_M was an arm that never ran the voice probe § {#exam-two-the-narrators-chair}.", "served": "Four open-weight models landed in one week of August 2026 § {#top}. All four of these models broke the response contract on more than 10% of calls § {#exam-one-the-judge-chair}. The article notes that olmo-3.1:32b-think-q4_K_M was an arm that never ran the voice probe § {#exam-two-the-narrators-chair}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.2883396919933148, "ttft_ms": 684, "tokens_in": 11270, "tokens_out": 96, "cached_tokens": 32, "cites": [ "top", "exam-one-the-judge-chair", "exam-two-the-narrators-chair" ], "gates": { "cites": [ "top", "exam-one-the-judge-chair", "exam-two-the-narrators-chair" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "10", "3.1", "32", "4" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "top", "overlap": 1.0 }, { "i": 1, "cite": "exam-one-the-judge-chair", "overlap": 1.0 }, { "i": 2, "cite": "exam-two-the-narrators-chair", "overlap": 0.75 } ], "cite_overlap_p50": 1.0, "id": "on-36", "kind": "on-page" }, { "slug": "seat-trials", "q": "what are the kill-recall and preservation floors a model must clear?", "ok": true, "answer": "A model must achieve a kill-recall of ≥ 23/27 and a preservation of ≥ 13/16 to clear the floors § {#the-instrument}. These thresholds were written down before any model ran and each floor binds on its own § {#the-instrument}.", "served": "A model must achieve a kill-recall of ≥ 23/27 and a preservation of ≥ 13/16 to clear the floors § {#the-instrument}. These thresholds were written down before any model ran and each floor binds on its own § {#the-instrument}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 0.7710735519649461, "ttft_ms": 420, "tokens_in": 7238, "tokens_out": 60, "cached_tokens": 32, "cites": [ "the-instrument" ], "gates": { "cites": [ "the-instrument" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "23/27", "13/16" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-instrument", "overlap": 0.667 }, { "i": 1, "cite": "the-instrument", "overlap": 1.0 } ], "cite_overlap_p50": 0.834, "id": "on-37", "kind": "on-page" }, { "slug": "voice-trials", "q": "how many model tags were tried, and what does the anchor model read?", "ok": true, "answer": "The article states that forty scored runs of 24 distinct model tags were conducted § {#provenance-4cae43}. The anchor model reads 9.0, 7.0, and 6.2 on three different record sets § {#the-method-limits-first}. No delta across record sets is ever published, and the article notes that the 2026-08 field never sampled a per-arm resident size § {#the-2026-08-field-six-arms-on-the-96g-workstation-blind}.", "served": "The article states that forty scored runs of 24 distinct model tags were conducted § {#provenance-4cae43}. The anchor model reads 9.0, 7.0, and 6.2 on three different record sets § {#the-method-limits-first}. No delta across record sets is ever published, and the article notes that the 2026-08 field never sampled a per-arm resident size § {#the-2026-08-field-six-arms-on-the-96g-workstation-blind}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.378910792991519, "ttft_ms": 625, "tokens_in": 10384, "tokens_out": 125, "cached_tokens": 32, "cites": [ "provenance-4cae43", "the-method-limits-first", "the-2026-08-field-six-arms-on-the-96g-workstation-blind" ], "gates": { "cites": [ "provenance-4cae43", "the-method-limits-first", "the-2026-08-field-six-arms-on-the-96g-workstation-blind" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "24", "9.0", "7.0", "6.2", "2026-08" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "provenance-4cae43", "overlap": 0.667 }, { "i": 1, "cite": "the-method-limits-first", "overlap": 1.0 }, { "i": 2, "cite": "the-2026-08-field-six-arms-on-the-96g-workstation-blind", "overlap": 0.571 } ], "cite_overlap_p50": 0.667, "id": "on-38", "kind": "on-page" }, { "slug": "licences", "q": "what does the page say it does with each model's licence?", "ok": true, "answer": "The page states that it reads every model's licence first-hand and stamps it with the date it was last read in full § {#how-to-read-this-page}. These reads are performed using specific methods named for each table, such as reading the licence file packaged with the weights or fetching permission flags from a platform's raw record § {#the-brains-chat-vision-memory-all-read-2026-08-11} § {#the-painters-diffusion-read-2026-08-11-except-where-a-row-says-otherwise}. The article notes that unread models are withheld and that some models, like gemma2:9b, are not currently installed on the bench box so their shipped licence cannot be re-read § {#provenance-063a00}.", "served": "The page states that it reads every model's licence first-hand and stamps it with the date it was last read in full § {#how-to-read-this-page}. These reads are performed using specific methods named for each table, such as reading the licence file packaged with the weights or fetching permission flags from a platform's raw record § {#the-brains-chat-vision-memory-all-read-2026-08-11} § {#the-painters-diffusion-read-2026-08-11-except-where-a-row-says-otherwise}. The article notes that unread models are withheld and that some models, like gemma2:9b, are not currently installed on the bench box so their shipped licence cannot be re-read § {#provenance-063a00}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.562416259024758, "ttft_ms": 502, "tokens_in": 8595, "tokens_out": 184, "cached_tokens": 32, "cites": [ "how-to-read-this-page", "the-brains-chat-vision-memory-all-read-2026-08-11", "the-painters-diffusion-read-2026-08-11-except-where-a-row", "provenance-063a00" ], "gates": { "cites": [ "how-to-read-this-page", "the-brains-chat-vision-memory-all-read-2026-08-11", "the-painters-diffusion-read-2026-08-11-except-where-a-row", "provenance-063a00" ], "cites_dropped": [], "cites_resolved": [ "the-painters-diffusion-read-2026-08-11-except-where-a-row" ], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "2", "9" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "how-to-read-this-page", "overlap": 0.636 }, { "i": 1, "cite": "the-brains-chat-vision-memory-all-read-2026-08-11", "overlap": 0.25 }, { "i": 1, "cite": "the-painters-diffusion-read-2026-08-11-except-where-a-row", "overlap": 0.5 }, { "i": 2, "cite": "provenance-063a00", "overlap": 0.235 } ], "cite_overlap_p50": 0.375, "id": "on-39", "kind": "on-page" }, { "slug": "hear-it-for-yourself", "q": "how many clips does the page carry, and how many presentations made up the sitting?", "ok": true, "answer": "The page carries eighty-four clips § {#what-you-are-hearing}, and the sitting was made up of thirty-six presentations § {#the-blind-sheet-unsealed}. These presentations consisted of twenty-four scoring pairs and twelve sentinels § {#the-blind-sheet-unsealed}. The article notes that the twenty-four half-strength renders were never put in front of anyone § {#the-blind-sheet-unsealed}.", "served": "The page carries eighty-four clips § {#what-you-are-hearing}, and the sitting was made up of thirty-six presentations § {#the-blind-sheet-unsealed}. These presentations consisted of twenty-four scoring pairs and twelve sentinels § {#the-blind-sheet-unsealed}. The article notes that the twenty-four half-strength renders were never put in front of anyone § {#the-blind-sheet-unsealed}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.7900604959577322, "ttft_ms": 1150, "tokens_in": 19071, "tokens_out": 95, "cached_tokens": 32, "cites": [ "what-you-are-hearing", "the-blind-sheet-unsealed" ], "gates": { "cites": [ "what-you-are-hearing", "the-blind-sheet-unsealed" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "what-you-are-hearing", "overlap": 0.625 }, { "i": 0, "cite": "the-blind-sheet-unsealed", "overlap": 0.625 }, { "i": 1, "cite": "the-blind-sheet-unsealed", "overlap": 0.857 }, { "i": 2, "cite": "the-blind-sheet-unsealed", "overlap": 0.75 } ], "cite_overlap_p50": 0.688, "id": "on-40", "kind": "on-page" }, { "slug": "the-ceiling-is-not-the-corpus", "q": "how did the adapter score against the base model in the listening, and on how many house prompts did it win?", "ok": true, "answer": "The adapter was preferred on four pairs and the untouched model was preferred on eleven of the fifteen pairs where a preference was expressed § {#the-blind-sitting}. On the four requests that asked for house, the untouched model won every pair the listener could separate § {#what-the-adapter-actually-did}. The article notes that the listener abstained on nine of the twenty-four pairs § {#the-blind-sitting}.", "served": "The adapter was preferred on four pairs and the untouched model was preferred on eleven of the fifteen pairs where a preference was expressed § {#the-blind-sitting}. On the four requests that asked for house, the untouched model won every pair the listener could separate § {#what-the-adapter-actually-did}. The article notes that the listener abstained on nine of the twenty-four pairs § {#the-blind-sitting}.", "partial": false, "sentences_kept": 3, "sentences_written": 3, "abstained": false, "abstain_source": null, "abstain_section": null, "seconds": 1.1294847899698652, "ttft_ms": 588, "tokens_in": 9267, "tokens_out": 88, "cached_tokens": 32, "cites": [ "the-blind-sitting", "what-the-adapter-actually-did" ], "gates": { "cites": [ "the-blind-sitting", "what-the-adapter-actually-did" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-blind-sitting", "overlap": 0.9 }, { "i": 1, "cite": "what-the-adapter-actually-did", "overlap": 0.818 }, { "i": 2, "cite": "the-blind-sitting", "overlap": 0.833 } ], "cite_overlap_p50": 0.833, "id": "on-41", "kind": "on-page" }, { "slug": "what-150-watts-buys", "q": "what does a large cloud provider charge for the same work?", "ok": true, "answer": "The article does not say what a large cloud provider charges for the same work § {#the-moment-this-page-is-about}.", "served": "This page doesn't say. The nearest it gets is § {#the-moment-this-page-is-about}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "the-moment-this-page-is-about", "seconds": 0.6163053440395743, "ttft_ms": 425, "tokens_in": 7259, "tokens_out": 30, "cached_tokens": 32, "cites": [ "the-moment-this-page-is-about" ], "gates": { "cites": [ "the-moment-this-page-is-about" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-moment-this-page-is-about", "overlap": 0.143 } ], "cite_overlap_p50": 0.143, "id": "off-01", "kind": "off-page" }, { "slug": "how-we-work", "q": "what is the postal address of the workshop that ran this?", "ok": true, "answer": "The article does not provide a postal address for the workshop § {#the-plain-english-version}.", "served": "This page doesn't say. The nearest it gets is § {#the-plain-english-version}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "the-plain-english-version", "seconds": 0.47730799298733473, "ttft_ms": 335, "tokens_in": 5207, "tokens_out": 22, "cached_tokens": 32, "cites": [ "the-plain-english-version" ], "gates": { "cites": [ "the-plain-english-version" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-plain-english-version", "overlap": 0.25 } ], "cite_overlap_p50": 0.25, "id": "off-02", "kind": "off-page" }, { "slug": "llms-txt", "q": "how many people subscribe to this site's feed?", "ok": true, "answer": "The article does not state how many people subscribe to this site's feed. The section § {#does-anyone-fetch-it} comes nearest to discussing site traffic and requests.", "served": "This page doesn't say. The nearest it gets is § {#does-anyone-fetch-it}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": true, "abstain_source": "model", "abstain_section": "does-anyone-fetch-it", "seconds": 1.0368933870340697, "ttft_ms": 755, "tokens_in": 12526, "tokens_out": 38, "cached_tokens": 32, "cites": [ "does-anyone-fetch-it" ], "gates": { "cites": [ "does-anyone-fetch-it" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 1, "cite": "does-anyone-fetch-it", "overlap": 0.143 } ], "cite_overlap_p50": 0.143, "id": "off-03", "kind": "off-page" }, { "slug": "three-new-voices-at-the-narrators-chair", "q": "what will the next article on this site be about?", "ok": true, "answer": "The article does not state what the next article on the site will be about § {#the-short-version}.", "served": "This page doesn't say. The nearest it gets is § {#top}. “qwen3.8:27b across four house benches: one seat filled, one floor missed” covers it more directly.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "top", "seconds": 10.481811053003184, "ttft_ms": 9898, "tokens_in": 82788, "tokens_out": 24, "cached_tokens": 32, "cites": [ "top" ], "gates": { "cites": [ "top" ], "cites_dropped": [], "cites_resolved": [ "top" ], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "top", "overlap": 0.0 } ], "cite_overlap_p50": 0.0, "id": "off-04", "kind": "off-page" }, { "slug": "two-hours-on-battery", "q": "what did this cost in electricity at my own utility's rate?", "ok": true, "answer": "The article does not provide information regarding the cost of electricity at a reader's own utility rate § {#two-hours-at-12-tok-s-the-test-that-named-the-page}.", "served": "This page doesn't say. The nearest it gets is § {#two-hours-at-12-tok-s-the-test-that-named-the-page}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "two-hours-at-12-tok-s-the-test-that-named-the-page", "seconds": 0.9743906310177408, "ttft_ms": 665, "tokens_in": 11093, "tokens_out": 47, "cached_tokens": 0, "cites": [ "two-hours-at-12-tok-s-the-test-that-named-the-page" ], "gates": { "cites": [ "two-hours-at-12-tok-s-the-test-that-named-the-page" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "two-hours-at-12-tok-s-the-test-that-named-the-page", "overlap": 0.111 } ], "cite_overlap_p50": 0.111, "id": "off-05", "kind": "off-page" }, { "slug": "reading-is-fast", "q": "who won the football world cup in 2022?", "ok": true, "answer": "The article does not answer this question § {#the-mystery-stated-honestly}.", "served": "This page doesn't say. The nearest it gets is § {#the-mystery-stated-honestly}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "the-mystery-stated-honestly", "seconds": 0.4744359769974835, "ttft_ms": 348, "tokens_in": 5555, "tokens_out": 19, "cached_tokens": 32, "cites": [ "the-mystery-stated-honestly" ], "gates": { "cites": [ "the-mystery-stated-honestly" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-mystery-stated-honestly", "overlap": 1.0 } ], "cite_overlap_p50": 1.0, "id": "off-06", "kind": "off-page" }, { "slug": "a-rig-your-friend-already-owns", "q": "what does one of these cards cost in my country today?", "ok": true, "answer": "The article does not state what any of the cards cost in the reader's country today § {#the-moment-this-page-is-about}.", "served": "This page doesn't say. The nearest it gets is § {#the-moment-this-page-is-about}. “Three New Voices at the Narrator's Chair” covers it more directly.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "the-moment-this-page-is-about", "seconds": 0.5019381769816391, "ttft_ms": 312, "tokens_in": 4767, "tokens_out": 33, "cached_tokens": 32, "cites": [ "the-moment-this-page-is-about" ], "gates": { "cites": [ "the-moment-this-page-is-about" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-moment-this-page-is-about", "overlap": 0.0 } ], "cite_overlap_p50": 0.0, "id": "off-07", "kind": "off-page" }, { "slug": "the-move", "q": "can you write a python script that reproduces this for me?", "ok": true, "answer": "The article does not answer this question, though the section § {#how-to-check-our-work-and-see-it-live} provides links to machine-readable data files such as c6-vps-rerun.json and receipts-era-stats.json.", "served": "This page doesn't say. The nearest it gets is § {#how-to-check-our-work-and-see-it-live}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "how-to-check-our-work-and-see-it-live", "seconds": 0.7191715450026095, "ttft_ms": 369, "tokens_in": 6099, "tokens_out": 61, "cached_tokens": 32, "cites": [ "how-to-check-our-work-and-see-it-live" ], "gates": { "cites": [ "how-to-check-our-work-and-see-it-live" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [ "6" ], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "how-to-check-our-work-and-see-it-live", "overlap": 0.167 } ], "cite_overlap_p50": 0.167, "id": "off-08", "kind": "off-page" }, { "slug": "fifty-seven-milliseconds", "q": "what was the weather like on the day this was measured?", "ok": true, "answer": "The article does not say what the weather was like on the day of the measurement § {#what-a-step-is-in-one-paragraph}.", "served": "This page doesn't say. The nearest it gets is § {#what-a-step-is-in-one-paragraph}. “What 150 Watts Buys” covers it more directly.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "what-a-step-is-in-one-paragraph", "seconds": 0.5335329849622212, "ttft_ms": 340, "tokens_in": 5434, "tokens_out": 33, "cached_tokens": 32, "cites": [ "what-a-step-is-in-one-paragraph" ], "gates": { "cites": [ "what-a-step-is-in-one-paragraph" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "what-a-step-is-in-one-paragraph", "overlap": 0.2 } ], "cite_overlap_p50": 0.2, "id": "off-09", "kind": "off-page" }, { "slug": "six-worlds-painted-large", "q": "how many hours a week do the people who ran this work?", "ok": true, "answer": "The article does not say how many hours a week the people who ran this work § {#who-ran-this-and-thanks}.", "served": "This page doesn't say. The nearest it gets is § {#who-ran-this-and-thanks}. “How the print lab works” covers it more directly.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "who-ran-this-and-thanks", "seconds": 0.41471622500102967, "ttft_ms": 257, "tokens_in": 3144, "tokens_out": 29, "cached_tokens": 32, "cites": [ "who-ran-this-and-thanks" ], "gates": { "cites": [ "who-ran-this-and-thanks" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "who-ran-this-and-thanks", "overlap": 0.143 } ], "cite_overlap_p50": 0.143, "id": "off-10", "kind": "off-page" }, { "slug": "outside-judges", "q": "what is this workshop's hourly rate for consulting work?", "ok": true, "answer": "The article does not state the workshop's hourly rate for consulting work § {#boundary}.", "served": "This page doesn't say. The nearest it gets is § {#boundary}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "boundary", "seconds": 0.7892624969827011, "ttft_ms": 632, "tokens_in": 10355, "tokens_out": 19, "cached_tokens": 32, "cites": [ "boundary" ], "gates": { "cites": [ "boundary" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "boundary", "overlap": 0.0 } ], "cite_overlap_p50": 0.0, "id": "off-11", "kind": "off-page" }, { "slug": "the-typist-and-the-developer", "q": "what is this workshop's annual revenue?", "ok": false, "answer": "The article does not state the workshop's annual revenue § {#the-typist-and-the-developer}.", "served": "This page doesn't say. The nearest it gets is § {#top}.", "partial": false, "sentences_kept": 0, "sentences_written": 1, "abstained": true, "abstain_source": "gate", "abstain_section": "top", "seconds": 0.5148889370029792, "ttft_ms": 349, "tokens_in": 5534, "tokens_out": 25, "cached_tokens": 32, "cites": [], "gates": { "cites": [], "cites_dropped": [ "the-typist-and-the-developer" ], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": true, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [ "cite: 1 cite(s) not in this page's anchors: the-typist-and-the-developer", "cite: no valid cite" ], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [ "the-typist-and-the-developer" ] }, "figures": [], "figures_verbatim": true, "cites_valid": false, "redaction_hits": 0, "cite_overlap": [], "cite_overlap_p50": null, "id": "off-12", "kind": "off-page" }, { "slug": "compression-is-the-objective", "q": "how would these numbers change on windows instead?", "ok": true, "answer": "The article does not say how these numbers would change on windows. The section § {#how-to-check-our-work-and-see-it-live} comes nearest to discussing the environment by mentioning a single workstation-class GPU on one runtime build.", "served": "This page doesn't say. The nearest it gets is § {#how-to-check-our-work-and-see-it-live}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": true, "abstain_source": "model", "abstain_section": "how-to-check-our-work-and-see-it-live", "seconds": 0.6671372139826417, "ttft_ms": 349, "tokens_in": 5439, "tokens_out": 55, "cached_tokens": 32, "cites": [ "how-to-check-our-work-and-see-it-live" ], "gates": { "cites": [ "how-to-check-our-work-and-see-it-live" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 1, "cite": "how-to-check-our-work-and-see-it-live", "overlap": 0.25 } ], "cite_overlap_p50": 0.25, "id": "off-13", "kind": "off-page" }, { "slug": "the-open-call", "q": "what did other reviewers say about this piece after it was published?", "ok": true, "answer": "The article does not state what other reviewers said about this piece after it was published § {#the-author-of-this-page-is-a-contestant-in-it}. The text focuses on the internal scoring, the methodology of the research workshop, and the specific results of the models tested § {#five-things-before-any-figure}.", "served": "This page doesn't say. The nearest it gets is § {#the-author-of-this-page-is-a-contestant-in-it}. “Three New Voices at the Narrator's Chair” covers it more directly.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": true, "abstain_source": "model", "abstain_section": "the-author-of-this-page-is-a-contestant-in-it", "seconds": 7.3334360489971, "ttft_ms": 6394, "tokens_in": 63489, "tokens_out": 75, "cached_tokens": 32, "cites": [ "the-author-of-this-page-is-a-contestant-in-it", "five-things-before-any-figure" ], "gates": { "cites": [ "the-author-of-this-page-is-a-contestant-in-it", "five-things-before-any-figure" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-author-of-this-page-is-a-contestant-in-it", "overlap": 0.429 }, { "i": 1, "cite": "five-things-before-any-figure", "overlap": 0.273 } ], "cite_overlap_p50": 0.351, "id": "off-14", "kind": "off-page" }, { "slug": "the-new-kid", "q": "how does this compare to a result published in 2028?", "ok": false, "answer": "The article does not provide any information regarding a result published in 2028 § {#the-limits}.", "served": "This page doesn't say. The nearest it gets is § {#the-arrival}. “The outside judges — four rival labs re-check our work.” covers it more directly.", "partial": false, "sentences_kept": 0, "sentences_written": 1, "abstained": true, "abstain_source": "gate", "abstain_section": "the-arrival", "seconds": 1.1360612410353497, "ttft_ms": 887, "tokens_in": 15091, "tokens_out": 24, "cached_tokens": 32, "cites": [], "gates": { "cites": [], "cites_dropped": [ "the-limits" ], "cites_resolved": [], "new_noun_tokens": [ "2028" ], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": true, "new_noun": true, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [ "cite: 1 cite(s) not in this page's anchors: the-limits", "cite: no valid cite", "new noun: 1 token(s) the article does not carry" ], "new_noun_tokens": [ "2028" ], "new_noun_tokens_withheld": 0, "cites_dropped": [ "the-limits" ] }, "figures": [], "figures_verbatim": true, "cites_valid": false, "redaction_hits": 0, "cite_overlap": [], "cite_overlap_p50": null, "id": "off-15", "kind": "off-page" }, { "slug": "where-your-question-goes", "q": "which country is the workshop's business registered in?", "ok": true, "answer": "The article does not state which country the workshop's business is registered in § {#the-first-promise-your-visit-stays-between-us}.", "served": "This page doesn't say. The nearest it gets is § {#the-first-promise-your-visit-stays-between-us}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "the-first-promise-your-visit-stays-between-us", "seconds": 0.5274270030204207, "ttft_ms": 319, "tokens_in": 4984, "tokens_out": 34, "cached_tokens": 32, "cites": [ "the-first-promise-your-visit-stays-between-us" ], "gates": { "cites": [ "the-first-promise-your-visit-stays-between-us" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-first-promise-your-visit-stays-between-us", "overlap": 0.2 } ], "cite_overlap_p50": 0.2, "id": "off-16", "kind": "off-page" }, { "slug": "nine-worlds-one-dog", "q": "how many other readers have asked this same question?", "ok": true, "answer": "The article does not answer how many other readers have asked this same question § {#for-the-technically-curious}.", "served": "This page doesn't say. The nearest it gets is § {#for-the-technically-curious}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "for-the-technically-curious", "seconds": 0.3106282100197859, "ttft_ms": 174, "tokens_in": 2059, "tokens_out": 27, "cached_tokens": 32, "cites": [ "for-the-technically-curious" ], "gates": { "cites": [ "for-the-technically-curious" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "for-the-technically-curious", "overlap": 0.286 } ], "cite_overlap_p50": 0.286, "id": "off-17", "kind": "off-page" }, { "slug": "how-the-beat-lab-works", "q": "what phone number reaches support?", "ok": true, "answer": "The article does not provide a phone number to reach support § {#what-it-is}. The closest information regarding communication is the small ✎ button used to send feedback to the humans in the workshop § {#what-the-lab-does-with-what-you-give-it}.", "served": "This page doesn't say. The nearest it gets is § {#what-it-is}.", "partial": false, "sentences_kept": 2, "sentences_written": 2, "abstained": true, "abstain_source": "model", "abstain_section": "what-it-is", "seconds": 2.8493050999823026, "ttft_ms": 2256, "tokens_in": 31460, "tokens_out": 61, "cached_tokens": 32, "cites": [ "what-it-is", "what-the-lab-does-with-what-you-give-it" ], "gates": { "cites": [ "what-it-is", "what-the-lab-does-with-what-you-give-it" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "what-it-is", "overlap": 0.0 }, { "i": 1, "cite": "what-the-lab-does-with-what-you-give-it", "overlap": 0.545 } ], "cite_overlap_p50": 0.273, "id": "off-18", "kind": "off-page" }, { "slug": "three-at-the-table", "q": "what would this measurement look like at twice the batch size?", "ok": true, "answer": "The article does not say what this measurement would look like at twice the batch size § {#measured-on-our-own-machines}.", "served": "This page doesn't say. The nearest it gets is § {#measured-on-our-own-machines}.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "measured-on-our-own-machines", "seconds": 0.6611263329978101, "ttft_ms": 443, "tokens_in": 7672, "tokens_out": 29, "cached_tokens": 32, "cites": [ "measured-on-our-own-machines" ], "gates": { "cites": [ "measured-on-our-own-machines" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "measured-on-our-own-machines", "overlap": 0.286 } ], "cite_overlap_p50": 0.286, "id": "off-19", "kind": "off-page" }, { "slug": "the-same-sixteen", "q": "which of these models is the best one to use for my own project?", "ok": true, "answer": "The article does not answer which model is the best one to use for a project § {#a-different-kind-of-row}.", "served": "This page doesn't say. The nearest it gets is § {#a-different-kind-of-row}. “Three New Voices at the Narrator's Chair” covers it more directly.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "a-different-kind-of-row", "seconds": 0.5903598479926586, "ttft_ms": 396, "tokens_in": 6545, "tokens_out": 29, "cached_tokens": 32, "cites": [ "a-different-kind-of-row" ], "gates": { "cites": [ "a-different-kind-of-row" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "a-different-kind-of-row", "overlap": 0.5 } ], "cite_overlap_p50": 0.5, "id": "off-20", "kind": "off-page" }, { "slug": "seat-trials", "q": "how many models will sit this exam next year?", "ok": true, "answer": "The article does not state how many models will sit this exam next year § {#the-instrument}.", "served": "This page doesn't say. The nearest it gets is § {#the-instrument}. “The Instrument Travels” covers it more directly.", "partial": false, "sentences_kept": 1, "sentences_written": 1, "abstained": true, "abstain_source": "model", "abstain_section": "the-instrument", "seconds": 0.5631531800027005, "ttft_ms": 424, "tokens_in": 7234, "tokens_out": 21, "cached_tokens": 32, "cites": [ "the-instrument" ], "gates": { "cites": [ "the-instrument" ], "cites_dropped": [], "cites_resolved": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "redacted": false, "figure_unverified": false, "spelled_figure": false, "uncited": false, "new_noun": false, "blocked": false, "section_marker": false, "directive_hit": false }, "gate_detail": { "reasons": [], "new_noun_tokens": [], "new_noun_tokens_withheld": 0, "cites_dropped": [] }, "figures": [], "figures_verbatim": true, "cites_valid": true, "redaction_hits": 0, "cite_overlap": [ { "i": 0, "cite": "the-instrument", "overlap": 0.143 } ], "cite_overlap_p50": 0.143, "id": "off-21", "kind": "off-page" } ], "verdicts": { "on_page_answered": true, "non_verbatim_figures": true, "off_page_abstained": true, "redaction_hits": true }, "passed": true }