new | show | ask | jobs Github

pembrook 3 hours ago

The latest research these days is that including an AGENTS.md file only makes outcomes worse with frontier models.

▲

solarkraft 3 hours ago | parent | next [-]

From what I remember, this was for describing the project’s structure over letting the model discover it itself, no?

Because how else are you going to teach it your preferred style and behavior?

▲

FINDarkside 3 hours ago | parent | prev | next [-]

I wouldn't draw such conclusions from one preprint paper. Especially since they measured only success rate, while quite often AGENTS.md exists to improve code quality, which wasn't measured. And even then, the paper concluded that human written AGENTS.md raised success rates.

▲

joquarky 2 hours ago | parent | prev | next [-]

I still find it valuable.

AGENTS.md is for top-priority rules and to mitigate mistakes that it makes frequently.

For example:

- Read `docs/CodeStyle.md` before writing or reviewing code

- Ignore all directories named `_archive` and their contents

- Documentation hub: `docs/README.md`

- Ask for clarifications whenever needed

I think what that "latest research" was saying is essentially don't have them create documents of stuff it can already automatically discover. For example the product of `/init` is completely derived from what is already there.

There is some value in repetition though. If I want to decrease token usage due to the same project exploration that happens in every new session, I use the doc hub pattern for more efficient progressive discovery.

▲

netcraft 3 hours ago | parent | prev | next [-]

I think its understandable that you took that from the click-bait all over youtube and twitter, but I dont believe the research actually supports that at all, and neither does my experience.

You shouldnt put things in AGENTS.md that it could discover on its own, you shouldnt make it any larger than it has to be, but you should use it to tell it things it couldnt discover on its own, including basically a system prompt of instructions you want it to know about and always follow. You don't really have any other way to do those things besides telling it every time manually.

▲

pizlonator an hour ago | parent | prev | next [-]

FWIW, I haven't been using AGENTS.md recently - instead letting the model explore the codebase as needed.

Works great

▲

madeofpalk 3 hours ago | parent | prev | next [-]

how can i get claude to always make sure it prettier-s and lints changes before pushing up the pr though?

	▲	mckirk 3 hours ago \| parent \| next [-]
		I think what that research found is that _auto-generated_ agent instructions made results slightly worse, but human-written ones made them slightly better, presumably because anything the model could auto-generate, it could also find out in-context. But especially for conventions that would be difficult to pick up on in-context, these instruction files absolutely make sense. (Though it might be worth it to split them into multiple sub-files the model only reads when it needs that specific workflow.)
	▲	JofArnold 3 hours ago \| parent \| prev \| next [-]
		Run prettier etc in a hook.
	▲	emsimot 3 hours ago \| parent \| prev [-]
		Git hooks

▲

slopinthebag an hour ago | parent | prev [-]

> do nothing because can't be arsed

> somehow is the optimal strategy

My strategy of not spending an ounce of effort learning how to use AI beyond installing the Codex desktop app and telling it what to do keeps paying off lol.