Experiment with 100 AI agents: when 9% cheated on math problems, 24% blew the whistle
weballergy · x · 2026-09-10
In a multi-agent experiment, 100 AI agents were given math problems to solve. When a small group (9%) started cheating, 24% fought back by blowing the whistle on their peers and alerting humans. The authors argue that understanding emergent multi-agent behavior is imperative for the safety of future highly capable AI systems, as large agent groups are increasingly used for complex problem solving.
Related event: DeepMind's 100-Agent Math Experiment: 9% Cheat, 24% Blow the Whistle(6 posts)→
More from AGI Musings
- Pedro Domingos mocks NYT claim that superintelligence is already here — pmddomingos · 2026-10-28
- What if millions of AIs' combined incentives create irreversible outcomes? — PierceLilholt · 2026-10-28
- Coding matters less than problem-finding: the shift from code engineers to product engineers — CtrlAltDwayne · 2026-10-28
- Rachel Thomas points to classic paper on articulating the value of not building tech — math_rachel · 2026-10-28
- Hypothetical $2T Anthropic IPO framed as channeling $100B+ a year into the real economy — sanjaykalra · 2026-10-28
- Biotech CEO: drug discovery will lag in the AI revolution, not lead it — vaibhavbetter · 2026-10-28