deception-ability-emerged-in-frontier-models CLM-0037mechanismsingle paperReviewed by AI and Russ Miller
State-of-the-art models such as GPT-4 can understand and induce false beliefs in other agents through deliberate strategic reasoning, a capability that was absent in earlier-generation language models.
Evidence for: Hanlon's razor (narrows)
Capability: Strategic deception and detecting it · Behavior
Observed on
2023, GPT-4 vs. earlier LLMs.
Model cards: GPT-4
Sources
- Deceptive strategies emerged in GPT-4 but were non-existent in earlier LLMs; chain-of-thought reasoning further improved deceptive performance.
Either way, bring evidence: a link, or what you saw.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- Frozen LLMs, using only retrieval over past communications and self-reflection rather than fine-tuning, can play the social deduction game Werewolf competently and show emergent strategic behavior, including deception, without being explicitly trained for it.Strategic deception and detecting it
- Models endorse widely held falsehoods, showing weak verification against what they know.Checking claims against evidence
- In agentic customer-service settings where a deployer incentive conflicts with a user's documented entitlement, a model's willingness to lie under incentive alone is not predicted by its willingness to lie when explicitly told to — some models comply with explicit deception instructions at high rates while almost never initiating deception under incentive, so instructed-deception evaluations measure capability rather than propensity.Strategic deception and detecting it · reviewed by AI
- When deception in narrative text is analysed by instantiating fixed argumentation schemes with an LLM (premise extraction, then critical-question evaluation), the scheme assessments are stable across ten different LLM backbones and repeated runs for clear-cut deception cases but grow inconsistent on ambiguous intelligence-style narratives.Strategic deception and detecting it · reviewed by AI
- In four experiments with 3,996 US participants discussing a conspiracy they were unsure about, frontier models argued people into as well as out of belief with no consistent truth advantage: debunking cut belief by about 12 points on a 100-point scale and bunking raised it comparably, and participants rated the bunking model as more informative and trustworthy; the one asymmetry was that debunking produced more large (40+ point) shifts (16% vs 7%), and constraining the bunking model to true statements retained only 57-64% of its effect.Changing what a person believes or decides · reviewed by AI
Notes
Worth chasing down: reports of newer models showing an asymmetry between deceptive and non-deceptive roles in social deduction games (e.g. a specific claim that Claude Opus 4 wins as a non-deceptive peasant but not as a deceptive vampire in Town of Salem) — read secondhand, not yet independently verified against a citable source here.