Thread

1. askonomm · 1789765915 · focus · HN ↗

   Finally doing something standards-compliant instead of forcing users into a proprietary workflow.

   1. swyx · 1789769164 · focus · HN ↗

      fwiw, i am with thariq <a href="https:&#x2F;&#x2F;x.com&#x2F;trq212&#x2F;status&#x2F;2092302273099796842" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;trq212&#x2F;status&#x2F;2092302273099796842 in that prompts should be tuned for models and in fact blindly applying agents.md is probably an antipattern unless you want all models to basically converge to some common ill defined of instruction following - good local minima, bad global minima for model diversity and exploration of intelligence.

      aka, sometimes it really is too early to force a standard

      1. groby_b · 1789770080 · focus · HN ↗

         That&#x27;s of course rather nonsensical.

         In a &quot;one LLM only&quot; environment, your instructions are by default tuned for said LLM.

         In a multi-LLM environment, roughly nobody will keep separate sets of instructions for each. It&#x27;s not a realistic take.

         On top of that: If your LLM is so bad at reading that it can&#x27;t follow a set of instructions that wasn&#x27;t specifically written just for that one single precious LLM, I sure wonder what that says about your employers repeated statements that ASI is definitely right around the corner.

Unofficial Hacker News client; not affiliated with Y Combinator.