Joschka Braun
@BraunJoschka
AI safety researcher @ApolloResearch | Science of Scheming | prev. @MATSprogram @kasl_ai @health_nlp @uni_tue
参加 April 2020
641 フォロー中 590 ファン
I’m giving a talk on exploration hacking with Safe AI Germany (SAIGE) today at 18:00 CEST.
I’ll discuss whether LLMs can learn to resist RL training, and why this matters for post-training and capability elicitation.
Join here:
もっと見る
