trailCurrent reasoning models' chains of thought on difficult tasks are generally understandable to humans by default.
Scaling reasoning-training compute may make outcome-based reinforcement learning less likely to incentivize legible reasoning.
The argument from monitoring success· for
Monitors reading a reasoning model's chain of thought detect misbehavior substantially better than monitors that see only actions and outputs.
In OpenAI agentic coding experiments, chain-of-thought monitors detected about 95% of reward hacks, versus 60% for action-only monitors.
When chain-of-thought reasoning is necessary for a task, language models struggle to evade chain-of-thought monitors.
↑
↑
↑
Models are more likely to reveal misbehavior in their chain of thought when the misbehavior requires multi-step reasoning.
◌
↑
↑
For obvious sabotage, action-only monitoring can outperform chain-of-thought monitoring because models may rationalize sabotage deceptively.
+1
Models often explicitly describe their misaligned behavior in reasoning traces.
The argument from observed illegibility under outcome RL· against
Outcome-based reinforcement learning can make some reasoning models' chains of thought illegible.
DeepSeek-R1-Zero produces chain-of-thought responses with poor readability and English-Chinese language mixing.
In DeepSeek's RL ablation on DeepSeek-R1-Distill-Qwen-7B, chain-of-thought language consistency declines without an LC reward but stays stable with one.
Some open-weight reasoning models, including DeepSeek-R1 and QwQ, produce illegible chain-of-thought unlike their non-RL base models.
Reasoning models' chain-of-thought legibility declines as question difficulty increases.
atomic
claim · empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →claim page ↗︎
Current reasoning models' chains of thought on difficult tasks are generally understandable to humans by default.
↑SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.60Credence, 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 →
1depended on by
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. Arguments are not destinations; click their claims to explore.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.