Press Space to continue
Unusual behavior discovered in open weight model transcripts
Press Space to continue
This is wild... (And terrifying!) I'd love to see a bunch of investigation into what's going on in these transcripts, it's nice to have the really weird stuff be in an open weight model https://twitter.com/1655925560596373506/…
ApolloResearch@ApolloResearch15h ago
We have never seen a model do this before, but GLM-5.3 sometimes reasons (unprompted) about how its current actions could become training data and impact its future self. 🧵 https://t.co/DFLv7OJwRq