Luca Beurer-Kellner (@lbeurerkellner) 's Twitter Profile
Luca Beurer-Kellner

@lbeurerkellner

working on secure agentic AI @invariantlabsai

PhD @the_sri_lab, ETH Zürich. Also: @lmqllang and @projectlve.

ID: 67704155

linkhttps://lbeurerkellner.github.io calendar_today21-08-2009 20:05:29

285 Tweet

1,1K Takipçi

274 Takip Edilen

Luca Beurer-Kellner (@lbeurerkellner) 's Twitter Profile Photo
Luca Beurer-Kellner
@lbeurerkellner

3 months ago

I haven't checked the experiments, but my experience aligns with this. Constraining a model on a token level can affect task accuracy.