Prime Intellect(@PrimeIntellect):The Goodfire team used Prime Intellect to train activation probes to detect reward hacking. With them, they are able to catch reward hacking in various models. Their probes are performing similarly or better than frontier LLM-as-judge setups, while being more efficient.

Prime Intellect

@PrimeIntellect

Open Superintelligence Stack

参加 June 2020

44 フォロー中 84.7K ファン

Prime Intellect@PrimeIntellect

2026.09.17 18:44

The Goodfire team used Prime Intellect to train activation probes to detect reward hacking. With them, they are able to catch reward hacking in various models. Their probes are performing similarly or better than frontier LLM-as-judge setups, while being more efficient.