trailVisible chain-of-thought traces make language-model behavior easier to monitor.
The argument from matched monitor comparisons· for
Monitors reading a reasoning model's chain of thought detect misbehavior substantially better than monitors that see only actions and outputs.
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
Reward hacks learned in realistic agentic coding RL typically require multi-step reasoning and exploration to discover and execute.
In OpenAI's monitorability evaluation suite, chain-of-thought-only monitors outperform monitors seeing only actions and final outputs.
atomic
The argument from necessary reasoning· for
Models are more likely to reveal misbehavior in their chain of thought when the misbehavior requires multi-step reasoning.
shared · shown elsewhere
When chain-of-thought reasoning is necessary for a task, language models struggle to evade chain-of-thought monitors.
shared · shown elsewhere
The argument that visibility is not monitorability· against
Reasoning models often omit from chain of thought hints or reward hacks that drive their answers.
shared · shown elsewhere
A chain-of-thought monitor can miss behavior even when the reasoning trace contains enough information to detect it.
atomic
The argument from concealing and misleading reasoning· against
Optimizing reasoning models' chains of thought against a monitor leads to reward hacking that the monitor cannot detect.
shared · shown elsewhere
Prompted or rewritten reasoning can make chain-of-thought monitors miss misbehavior they would otherwise detect, without model training.
atomic
For obvious sabotage, action-only monitoring can outperform chain-of-thought monitoring because models may rationalize sabotage deceptively.
atomic
claim · causalA claim that one thing brings about another, not merely that the two go together.constitution →claim page ↗︎
Visible chain-of-thought traces make language-model behavior easier to monitor.
↑SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.85Credence, 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.