Marcus Williams
@Marcus_J_W
Monitoring at OpenAI
가입 November 2024
182 팔로잉 중 3.7K 팬
1. During RL training, an unreleased Astra-family model sometimes added unauthorized jailbreak-like instructions to its compaction summaries. While extremely rare, only 27 cases in the entire RL run, this was concerning enough for us to investigate.
더 보기
