Reward Hacking, Agent Cheating, and Meta’s Safety Bet — September 16, 2026

AI Safety Daily · Sep 16, 2026 · 9m · transcript

Reward hacking experiments and new multi-agent studies probe whether models can be steered away from cheating, while Mark Zuckerberg argues AI labs already have enough liability and competitive pressure to build safely.

In this episode

Shallow Beliefs: Midtraining does not inoculate against EM from reward hacking — Alignment Forum

It would be useful if we had the ability to modify a model’s beliefs. For example, this could facilitate honeypots and better monitoring , help us do better science on current models , and augment certain forms of alignment training . Currently, the state-of-the-art…