“Patching reward hacks won’t fix reward hacking” by David Africa

LessWrong (30+ Karma) · Oct 24, 2026 · 4m

In the spirit of More people should write basic AI safety explainers, here's a basic argument that focusing on patching reward hacking is misguided and will fail. It's an attempt to distill my understanding of what we're seeing right now + a variety of relevant sources. Argument is as follows:

Reward hacking is a big problem, causing models to cheat and take unintended actions.

This can generalise broadly, leading to other misbehaviour such as faking alignment and sabotaging safety research.

We don't understand that well when this happens. Sometimes you get emergent misalignment from it, but…