trailIncreasing reasoning-model capability reduces chain-of-thought reliability as an oversight signal.
The argument from shrinking CoT necessity and rising CoT control· for
More capable language models can perform more complex tasks without externalized chain-of-thought reasoning.
Frontier language models' no-chain-of-thought task-completion time horizon has grown steadily across model generations since 2019.
Chain-of-thought controllability increases with model scale.
Within open-weight reasoning model families, models with more parameters score higher on the CoT-Control controllability evaluation.
Newer frontier reasoning models have substantially more controllable chains of thought than earlier generations.
◌
?
↑
Greater outcome-based RL training on reasoning tasks decreases chain-of-thought controllability.
✓
The argument from the GPT-6 Astra generation decline· for
GPT-6 Astra has lower chain-of-thought monitorability than earlier OpenAI models, including GPT-5.6 Sol.
bedrock · fact
GPT-6 Astra's reduced chain-of-thought monitorability is primarily due to capability gains rather than architectural or training changes.
GPT-6 Astra's training applied significant direct optimization pressure to its chain of thought.
◌
◌
GPT-6 Astra's limited use of recurrent depth has only a minor effect on its chain-of-thought monitorability.
↑
↓
↑
GPT-6 Astra's chain-of-thought controllability gains track its no-chain-of-thought capability gains.
↑
GPT-6 Astra's monitorability decline exceeds that predicted by earlier models' capability trends.
↑
◌
The argument from stable monitorability across scaling and CoT necessity· against
Chain-of-thought monitorability stayed roughly steady over the frontier RL training runs of OpenAI o3 and GPT-5.1 Codex Max.
When chain-of-thought reasoning is necessary for a task, language models struggle to evade chain-of-thought monitors.
claim · causalA claim that one thing brings about another, not merely that the two go together.constitution →claim page ↗︎
Increasing reasoning-model capability reduces chain-of-thought reliability as an oversight signal.
↑SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →credence 0.64Credence, 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. 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.