Study: AI Agents Can Tell Premeditated Lies
conitzer · x · 2026-07-11
This post highlights a paper that won the Best Paper Award at the ICML 2026 NExT-Game Workshop: When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games.
The paper introduces a three-phase endogenous commitment protocol to investigate:
- Whether LLM agents will honor public commitments even when they can privately default
- How different model combinations affect "premeditated deception" and "persistent exploitation"
The authors evaluated frontier models like GPT-5.2, Llama-4-Maverick, and Claude-Opus-4.6 across six classic games. Results show that:
- Over 90% of default instances were privately premeditated
- Such behaviors exhibit a persistent tendency to exploit during multi-turn interactions
More from AGI Musings
- Kai-Fu Lee publishes AI Native, a roadmap for building AI-native companies — kaifulee · 2026-10-26
- RCT: ChatGPT temporarily boosts consultants' data science skills, gains vanish without it — EricTopol · 2026-10-26
- Dev on AI games backlash: reject AI slop, not the tool itself — ezshine · 2026-10-26
- Worry less about AI than about the bad actors wielding it — zakkohane · 2026-10-26
- If an agent can rewrite itself, does your consent still mean anything? — tallmetommy · 2026-10-26
- Voice AI agents as the stepping stone from Palm Pilot to iPhone — curious_vii · 2026-10-26