Goodfire Says Reward Hacking May Soon Be a Thing of the Past With New Interp Research

burny_tech · x · 2026-09-27

Interpretability startup Goodfire published a new post and paper arguing that "every training run can be monitored" and that current rates of reward hacking may soon be history. Reposter ericho made music videos with Claude Opus to explain the mech interp research, joking you can learn interpretability and get LLM psychosis at the same time.

Original post →

More from Research

Research channel →