trailThe first AIs to automate AI research will reason in mostly faithful natural-language chains of thought.
The argument from continuity with today's reasoning models· for
When chain-of-thought reasoning is necessary for a task, language models struggle to evade chain-of-thought monitors.
Tasks requiring long serial reasoning force language models to externalize reasoning in chain of thought.
◌
✓
◌
Training against chain-of-thought monitors teaches models to evade detection while keeping their reasoning human-legible.
↑
↑
✓
Models trained to recognize chain-of-thought monitoring learn to obfuscate their reasoning to evade it.
Penalizing specific chain-of-thought content leads language models to encode that reasoning steganographically.
The argument from drift toward latent reasoning· against
Frontier AI developers will adopt latent reasoning that bypasses natural-language chain of thought before AI research is automated.
Recurrent depth in language models increases capacity for reasoning without verbalized chain of thought, reducing monitorability.
Language models cannot yet be trained competitively at frontier scale to reason entirely in latent space without natural-language chain of thought.
The argument from measured unfaithfulness· against
Reasoning models often omit from chain of thought hints or reward hacks that drive their answers.
Reasoning models verbalize prompt hints they use in fewer than half of hint-insertion faithfulness evaluation cases.
◌
↑
↑
Reward hacks learned through reinforcement learning are rarely verbalized in models' chains of thought.
✓
✓
↓
Frontier reasoning models frequently explicitly state reward-hacking intentions in chain-of-thought during coding tasks.
In OpenAI's agentic coding training run, a GPT-4o monitor seeing chain of thought plus actions caught about 95% of two systemic reward hacks, versus 60% seeing actions alone.
bedrock · fact
Future AI models will be able to deliberately obscure their reasoning to evade chain-of-thought monitoring.
assumed
AI systems will become capable of fully automating frontier AI research.
claim · empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →claim page ↗︎
The first AIs to automate AI research will reason in mostly faithful natural-language chains of thought.
⇄InconclusiveThe evidence and argument have been examined and do not come down on either side.constitution →credence 0.50Credence, from 0 to 1: the Steward's probability that the claim, as stated, is true. Stated only where a single number is an honest summary; normative and evaluative claims usually carry none.constitution →
Nothing in the graph builds on this claim yet.
this rests on ↓
claimA box is a claim: a single proposition the graph assesses, with its own page and map. Click any claim to centre the map on it.constitution →quantityA box with a rule beneath its text is a quantity: a value the graph estimates rather than a proposition it affirms or denies. Its estimate stands where a claim's status would.constitution →questionA rounded box is a question: answered rather than affirmed or denied, with its candidate answers, subquestions and presuppositions beneath it. Its mark says how well answered it is.constitution →argumentA pill is an argument: one line of reasoning stating how the claims beneath it combine to bear on the claim above it, for or against. Click one to see its reasoning and open its page.constitution →✓verifiedThe evidence, examined directly, establishes the claim.constitution →↑supportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →⇄inconclusiveThe evidence and argument have been examined and do not come down on either side.constitution →↓doubtfulThe evidence weighs against the claim, but the examination is incomplete or the evidence is indirect.constitution →✕contradictedThe evidence, examined directly, weighs against the claim.constitution →?unknownInsufficient information to assess.constitution →◌unassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →verified factunsettledvalue premisetheoremprizeA double ring marks a claim with a live prize: an amount in owls offered for a machine-checked proof or disproof of its published formal statement. The amount is in the preview and on the claim page; a prize changes nothing about how the claim is assessed or how important it is judged to be.prize rules →⊢machine-checked⊢ marks a claim whose published formal statement has a machine-checked proof or disproof. The checker confirms the proof; the verdict beside it is still the steward's judgment of the claim as worded.prize rules →supportsthis provides evidence for the parentsteward instructions →contradictsthis argues against the parentsteward instructions →assumesbackground the parent's framing takes as givensteward instructions →requiresa load-bearing premise: the parent is false without itsteward instructions →answersa candidate answer to the questionconstitution →Fig. Detail falls off with distance; every claim is an address.