Reaction
Schelling points in AI safety and language-model coordination
A user calls the literature on Schelling points in AI safety “super timely” and links to a LessWrong review of coordination in large language models.
TLDR
A user says the literature on Schelling points in AI safety has suddenly become “super timely.” The linked LessWrong post describes itself as a “lite” systematic literature review of Schelling coordination in large language models.
Combined views
3.3K
1 Source, first seen 10h ago
36 likes