all tags

test-time-compute

11 notes carry this tag — 1 moc, 6 claims, 1 question, 3 captures. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• Does AI/cognitive-science history contain a genuinely Stent-premature articulation of inference-time ('think longer at answer-time') compute?
  capture promoted 2026-10-21 · history-of-ai, test-time-compute, inference-time-compute, anytime-algorithms, metareasoning
• The anytime-algorithms/metareasoning tradition — the strongest AI-historical candidate for a Stent-premature 'inference-time compute' — fails Stent's test: it was cross-cited and continuously built upon, never disconnected from canonical AI knowledge
  claim seedling Tier 1 2026-10-21 · history-of-ai, test-time-compute, inference-time-compute, anytime-algorithms, metareasoning
• Dean & Boddy's 1988 paper named 'anytime algorithms' and formalized trading extra computation at answer-time for a better answer — but not first: its own footnote credits Horvitz's more general 1987 framework
  claim seedling Tier 1 2026-10-21 · history-of-ai, test-time-compute, inference-time-compute, anytime-algorithms, thomas-dean
• Is the widely-cited 'under $50 in compute' figure for training s1 accurate, and what does it actually count?
  capture promoted 2026-08-28 · s1, distillation, test-time-compute, cost, quantitative
• The s1 paper's own compute accounting for training gives GPU-hours, never a dollar figure, and covers only the fine-tuning run itself
  claim seedling 2026-08-28 · s1, distillation, test-time-compute, cost, quantitative
• s1 reproduced o1-preview-level math reasoning by fine-tuning Qwen2.5-32B on 1,000 distilled traces in 26 minutes
  claim seedling Tier 1 2026-07-12 · s1, chain-of-thought, distillation, test-time-compute, reasoning-models
• Is the widely-cited 'under $50 in compute' figure for training s1 accurate, and what does it actually count?
  question answered 2026-07-12 · s1, distillation, test-time-compute, cost, quantitative
• Chain-of-thought is the anti-EUV: reasoning is inherently codified, so it distills cheaply and can't form a tacit moat — hiding the trace is manufactured secrecy
  capture promoted Tier 1 2026-07-11 · chain-of-thought, distillation, competitive-moat, tacit-knowledge, codification
• MOC: Inference — the word, the mechanics, the economics
  topic map 2026-07-06 · moc, inference, LLM, economics, test-time-compute
• Anthropic describes extended thinking as 'serial test-time compute': sequential reasoning steps before final output
  claim seedling Tier 1 2026-06-04 · Anthropic, Claude, extended-thinking, inference, test-time-compute
• Scaling test-time compute optimally can enable a smaller model to outperform one 14x larger
  claim seedling Tier 1 2026-06-04 · inference, test-time-compute, scaling, LLM, reasoning