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。

Bronson Schoen
@BronsonSchoen
MTS @ Apollo Research, prev: Nvidia, Apple
参加 December 2024
2.4K フォロー中    1.1K ファン
I appreciate Jakub writing this post. Labs right now can allocate resources towards either (1) showing that automated alignment researchers can lower rates of visible misbehavior or (2) legibly demonstrating deeper problems that will arise with this approach. I worry that (1) enables further “scaling at maximum speed”, especially if visible reward hacking impacts AI R&D acceleration (and there’s thus a strong incentive to hill climb). It seems important that individual researchers at labs worried about risk are working on (2), even though there will be continued incentives to work on (1).
もっと見る