Padarn

[Padarn @Padarn]

@swyx there is a yaml frontmatter bug in a codebase-maintainability-guardrails/SKILL.md FYI

[Padarn @Padarn]

@rvtond Why can’t you just deny all tools except the code execution one? https://t.co/5K4O8fpepq

[Padarn @Padarn]

@shi_weiyan Thanks! I don't see the recording at the link though?

[Padarn @Padarn]

@shi_weiyan @jaseweston Is there a recording? Looks great!

[Padarn @Padarn]

@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.

[Padarn @Padarn]

@athyuttamre @mitsuhiko Is there any way to extend the retention? Does the whole thread expire at 30d or just the stored state of some response_ids?

[Padarn @Padarn]

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'?

[Padarn @Padarn]

@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?

[Padarn @Padarn]

@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

[Padarn @Padarn]

@AmazonScience @WSDMSocial Great work! Will it be available on github anytime soon?

[Padarn @Padarn]

@ezyang I couldn’t find it :sad:

[Padarn @Padarn]

@rakyll Curious what, if any, tools you're using to do this? I've found copilot only "okay" as an experience to do test driven LLM development.

[Padarn @Padarn]

@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!

[Padarn @Padarn]

@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.

[Padarn @Padarn]

@thorstenball Seems like this got Amazon a lot of free advertising for a feature… maybe it’s all working out?

[Padarn @Padarn]

@ChinmayaKausik @eytan @ZheqingZhu @AIatMeta I’d be fascinated to know how people use these paradigms together?

[Padarn @Padarn]

@airvistara hello can you help me with a lost Apple Watch on a flight?

The flight was from Delhi to Singapore, UK115, leaving 23:45 27th of November

[Padarn @Padarn]

@testingham (Off topic: Sad those abstracts are not published)