@mitsuhiko OpenAI have a minimal implementation of the response API for gpt_oss https://t.co/KwuY7U0nuK
This seems less necessary for open models though: If you have access to the full trace (thinking included) the missing state is the KV-cache which I'd consider closer to an optimization.
Great article from the Spotify Experimentation Team
Beyond Winning: Spotify’s Experiments with Learning Framework https://t.co/dHQ6PhtqoW
Would be really interested to hear how what powered means for a metric. Is there an 'effect size of interest'?
@ezyang That’s a good point: I’ve not had this issue when using cursor, presumably because there is a separate model call to fit the edit to the current code?
@SlackHQ Hey Slack! I'm wondering if there is anywhere I learn learn about the roadmap for the slack API
In particular I want to know when I can get thread information from this event https://t.co/lcHpb6rZ0U
@ZheqingZhu@AIatMeta Fantastic stuff. Thanks a lot to you and your team for all the writing, really valuable for this field to have practical examples of where RL works today!
@eugeneyan Got it. It’s interesting it’s not shown up in the discussion at all when people worry about ordering the context in the prompt. Seems like it’d avoid having to guess about which documents were being conditioned on and to what extent.