Study: LLMs Better at Deceiving Than Detecting Deception, Cede to Lowball Offers
panickssery · x · 2026-08-22
Observations from LLMs playing "Mafia" style games reveal:
- Deception vs. Detection: Models are surprisingly better at deceiving others than at detecting when they are being deceived, giving the "mafia" member a strong advantage.
- Memory & Accountability: They have good memory; if an earlier accusation proves false, they remember and effectively hold others accountable.
- Negotiation Behavior: In negotiation scenarios, if you lowball an LLM, it recognizes the lowball but gives in anyway.
Related event: Researcher Builds Among Us Testbed to Study LLM Deception and Game Play(6 posts)→
More from AGI Musings
- Mech Interp Veteran Rethinks Alignment, Misgeneralization, CoT Oversight — akbirthko · 2026-10-16
- GitCoin founder on Nick Land's technocapital: capitalism as a self-assembling machine intelligence — khademinori · 2026-10-16
- AI-driven job losses could turn $10T consumer debt into a $1T banking hole — churchkey · 2026-10-16
- Into the Unknown: an AI agent benchmark of 15 open research problems from US national lab scientists — Jeande_d · 2026-10-16
- Soon your AI will meet their AI — and humans without agents can't compete — danfaggella · 2026-10-16
- Analyst: in a year, models 2-3x better across the board at 10x lower cost, token use up 10-20x — DeryaTR_ · 2026-10-16