Hacker News new | ask | show | jobs
by embedding-shape 80 days ago
Issue is that both harness and specific model matters a lot in what type of instruction works best, if you were to use Anthrophic's models together with the best way to do prompting with Codex and GPT models, you'd get a lot worse results compared to if you use GPT models with Codex, prompted in the way GPTs react best to them.

I don't think people realize exactly how important the specific prompts are, with the same prompt you'd get wildly different results for different models, and when you're iterating on a prompt (say for some processing), you'd do different changes depending on what model is being used.
2 comments
freedomben 80 days ago
Having experimented with soft-linking AGENTS.md into CLAUDE.md and GEMINI.md, this lines up well with my experience. I now just let each time maintain it's own files and don't try to combine them. If it's something like my custom "## Agent Instructions" then I just copy-pasta and it's not been hard, and since that section is mostly identical I just treat AGENTS.md as the canonical and copy/paste any changes over to the others.
link
NomDePlum 80 days ago
If you create a CLAUDE.md with contents of @AGENTS.md that works and has the added benefit of allowing Claude specific instructions too, to be added below.
link
dbmikus 80 days ago
Are there any good guides on how to write prompt files tailored to different agents?

Would also be interested in examples of a CLAUDE.md file that works well in Claude, but works poorly with Codex.

link
dhorthy 80 days ago
I think one of the main examples that i saw in a swyx article a while back is that using the sort of ALL CAPS and *IMPORTANT* language that works decently with claude will actually detune the codex models and make them perform worse. I will see if I can find the post
link
flyingcircus3 80 days ago
Why would you settle for a guide when you can get a claude skill to do it for you?

https://github.com/nidhinjs/prompt-master

link
KiaKatt 80 days ago
Because that just does it for you, it doesn't help me understand how to write better prompts.

Actually, I can just read the skill with my own eyes and then I can also learn. So, thank you for sharing. It's interesting to read through what it suggests for different models - it fits for the ones I work with regularly, but there are many I don't know the strengths and weaknesses of.

link