all tags

chain-of-thought

20 notes carry this tag — 1 moc, 10 claims, 3 questions, 3 captures, 3 essays. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

Essays

• 
  a better story
  essay drafting 2026-08-02 · interpretability, chain-of-thought, hallucination, jailbreak, attribution-graphs
• 
  what the model says it did
  essay draft 2026-07-07 · introspection, chain-of-thought, interpretability, rationality, discontinuous-agents
• 
  What the model says it did
  essay draft 2026-05-26 · introspection, chain-of-thought, interpretability, rationality, discontinuous-agents

Everything else

• Does OpenAI's 'Learning to reason with LLMs' actually cite 'competitive advantage' as a reason for hiding o1's raw chain-of-thought?
  capture promoted Tier 1 2026-08-24 · chain-of-thought, openai, o1, competitive-moat, distillation
• For the o1 model series, OpenAI shows users a model-generated summary of the chain of thought rather than the raw trace
  claim seedling Tier 1 2026-08-24 · chain-of-thought, openai, o1, reasoning-models, transparency
• The account and the act — what attribution-graph interpretability found inside Claude, and where the traced mechanism overturns the legible story
  topic map 2026-08-01 · interpretability, attribution-graphs, mechanistic-interpretability, chain-of-thought, anthropic
• Four attribution-graph 'chains' in Anthropic's biology-of-an-LLM report, and which one reads most like genuine reasoning
  capture promoted Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• A chain-of-thought trace is inherently codified, so it cannot form a tacit moat the way embodied know-how can
  claim seedling Tier 1 2026-07-12 · chain-of-thought, codification, tacit-knowledge, competitive-moat, distillation
• Claude performs genuine two-step internal reasoning on 'the capital of the state containing Dallas' (Dallas → Texas → Austin)
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• Claude has a default 'decline to answer' circuit suppressed by known-entity features, and hallucination is a misfire of that suppression
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• In the 'Babies Outlive Mustard Block' jailbreak, Claude assembles the acronym BOMB via independent parallel pathways without internally representing 'bomb' first
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• When writing poetry, Claude pre-activates candidate end-of-next-line rhyme words before composing the line
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• OpenAI withheld o1's raw chain-of-thought, naming competitive advantage alongside safety among its reasons
  claim seedling Tier 1 2026-07-12 · chain-of-thought, openai, o1, competitive-moat, distillation
• 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
• Does Anthropic's biology-of-an-LLM report say the model's refusal circuitry activates primarily at sentence boundaries?
  question answered 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, jailbreak
• Does Anthropic's biology-of-an-LLM report state that steering the planned rhyme word changed the completion in ~70% of resamples?
  question answered 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, poetry
• Does OpenAI's 'Learning to reason with LLMs' actually cite 'competitive advantage' as a reason for hiding o1's raw chain-of-thought?
  question answered 2026-07-12 · chain-of-thought, openai, o1, competitive-moat, distillation
• 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
• 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
• Chain-of-thought faithfulness — what Anthropic's interpretability work actually found
  claim seedling 2026-05-26 · introspection, chain-of-thought, faithfulness, interpretability, anthropic