Findings from a Pilot Anthropic - OpenAI Alignment Evaluation Exercise
Findings from a Pilot Anthropic—OpenAI Alignment Evaluation Exercise Samuel R. Bowman, Megha Srivastava, Jon Kutasov, Rowan Wang, Trenton Bricken, Benjamin Wright, Ethan Perez, and Nicholas Carlini tl;dr In early summer 2025, Anthropic and OpenAI agreed to evaluate each other's public models using in-house misalignment-related evaluations. We are now releasing our findings in parallel. The evaluat
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Petri 2.0: New Scenarios, New Model Comparisons, and Improved Eval-Awareness Mitigations
