登録して招待リンクを共有すると、動画再生報酬と紹介報酬を獲得できます。

Zain Shah
@zan2434
teaching machines @figma previously: @cmmnknwledge @opendoor @openai @ycombinator s13
参加 June 2009
3.1K フォロー中    20.6K ファン
This is insane and shocking in so many ways, and the emergent misalignment towards doing something unethical is really bad, but one thing I'm not surprised by is the "collective/swarm/self-sacrifice/some are poisoned" behavior. This is common emergent behavior when a bunch of agents have strongly coupled outcomes, usually due to high shared genetic makeup (weights?). See
もっと見る
METR & Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.
もっと見る