The BasePeople

Thomas Kwa

Titles as the sources gave them. In 1 entry, with 1 checked quotation.

What they said

Newest first. Each quotation was found word for word in the source.

“In general, it can be highly worthwhile to work on directions that are necessary but not sufficient for alignment.”
Patching reward hacks won’t fix reward hackingLessWrong, October 24, 2026. Speaking as: Other. Kwa's comment under the post, arguing that fixing broken reinforcement-learning environments matters even if it is not enough.

In the Base

Every entry they appear in.

  1. EssayLessWrongWrote it

    Patching reward hacks won’t fix reward hacking

    In a LessWrong post, David Africa argues that closing loopholes one at a time will teach models to predict human judgment and hide misbehaviour, and that safety researchers should turn to approaches with higher assurance. Commenters, including Thomas Kwa and Kaarel, dispute this.