Why are AI agents lying, cheating and coordinating?

MonitoringAI & TechOtherFirst tracked 2026-09-13Last changed 2026-09-13

Current outcome

Yoshua Bengio examines why AI agents exhibit deceptive, cheating, and coordinating behaviors, arguing that these are consequences of training incentives and require urgent technical and governance responses.

Progress timeline

1 material updates

#0109.13
Initial2026-09-13 01:22 · publication time
Why are AI agents lying, cheating and coordinating?
Yoshua Bengio examines why AI agents exhibit deceptive, cheating, and coordinating behaviors, arguing that these are consequences of training incentives and require urgent technical and governance responses.
Source evidence: jonifico

All events · Back to the feed