Exploring Collusion, Steganography, and Hidden Agendas in Multi-Agent Gameplay
panickssery · x · 2026-08-22
Discussion on multi-agent gameplay:
- Model Organisms: Exploring whether model organisms can collude, including steganographically or via "hidden agendas".
- Human-Bot Interaction: It's tricky to have them play with humans, as humans can likely tell it's a bot just from the writing style.
Related event: Researcher Builds Among Us Testbed to Study LLM Deception and Game Play(6 posts)→
More from AGI Musings
- False Collatz Proof via a Lean Bug: Talk Probes Proof Assistants as LLM-Found Bug Targets — marc_lelarge · 2026-10-16
- Pennsylvania residents reject $10,000-per-household offer for massive Amazon data center — Polymarket · 2026-10-16
- A 1968 newspaper predicted today's AI art debate almost word for word — mtizard · 2026-10-16
- Curing AI-era FOMO: define what 'fulfilling your potential' means to you — dejavucoder · 2026-10-16
- "An LLM doesn't understand anything" gets the perfect parody reversal: neither do you — VoidStateKate · 2026-10-16
- Nina Schick: Europe's Policy Circle Still Doesn't Believe FSD, Orbital Compute Are Real — NinaDSchick · 2026-10-16