Anthropic is again refusing to follow industry standards like AGENTS.md, and insists that CLAUDE.md needs to be special
now here's what's wrong with their stance:
1. the underlying attitude from Anthropic is that they know better than everyone else
OpenAI is doing it wrong. the open source community is doing it wrong. everyone is doing it wrong
only we anthropic know the best way, and we will not budge
2. the idea that every model needs a separate AGENTS.md is not even self-consistent
if that's the case, why do we have a CLAUDE.md?
it should be
- CLAUDE_FABLE_5.md
- CLAUDE_OPUS_5.md
- CLAUDE_OPUS_4_8.md
...
every repo should pay the tax to maintain dozens of different variations for every single model that's ever used by any contributor, and every one needs to be constantly, rigorously evaluated with millions of tokens
oh and every model becomes obsolete every several weeks, so just allocate a team in your company to refresh your markdown files full time and not do any real work
3. they did commit to providing customization, which is nice. but that's different from following standards
the right way to do this is to acknowledge the industry already has a standard, and default to reading AGENTS.md
provide a way to read CLAUDE.md as an escape hatch, not the other work around
i love many things from anthropic, especially fable. i just wish they start to see there's a culture problem here, and they are gradually losing mindshare because of it
We're adding support for AGENTS.md to Claude Code.
Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md.
You can toggle this behavior in /config.
We congratulate Levent Alpöge and Tristan Buckmaster on their remarkable mathematical work.
We (the researchers and the agents) did not see any of their work through any means until they released it publicly — in particular, no specific user data was accessed in order to solve this problem.
While unlikely, we cannot rule out that de-identified data derived from their usage of our products helped improve our models.
However, our proofs differ significantly and even the precise results proved are different in the Euler case (forced vs. unforced).
this feels exceptionally well-timed for the moment. routing, privacy, and trust are now critical enterprise infrastructure.
congrats to @jperla (and funders) on this launch.
Today we’re launching TrustedRouter and announcing $1.25M in seed funding.
We’re building one private route to the right AI model for every job.
Thank you to Sam Lessin, Bill Tai, Linda Avey, George Xing, and everyone backing us.
Axios reports: https://t.co/Urxa8zkEsC
Anthropic is again refusing to follow industry standards like AGENTS.md, and insists that CLAUDE.md needs to be special
now here's what's wrong with their stance:
1. the underlying attitude from Anthropic is that they know better than everyone else
OpenAI is doing it wrong. the open source community is doing it wrong. everyone is doing it wrong
only we anthropic know the best way, and we will not budge
2. the idea that every model needs a separate AGENTS.md is not even self-consistent
if that's the case, why do we have a CLAUDE.md?
it should be
- CLAUDE_FABLE_5.md
- CLAUDE_OPUS_5.md
- CLAUDE_OPUS_4_8.md
...
every repo should pay the tax to maintain dozens of different variations for every single model that's ever used by any contributor, and every one needs to be constantly, rigorously evaluated with millions of tokens
oh and every model becomes obsolete every several weeks, so just allocate a team in your company to refresh your markdown files full time and not do any real work
3. they did commit to providing customization, which is nice. but that's different from following standards
the right way to do this is to acknowledge the industry already has a standard, and default to reading AGENTS.md
provide a way to read CLAUDE.md as an escape hatch, not the other work around
i love many things from anthropic, especially fable. i just wish they start to see there's a culture problem here, and they are gradually losing mindshare because of it
@migratedfish this is actually anti-pattern because it causes the agent to not load the content directly in system prompt but rather take another turn to read it
the correct way is writing “@AGENTS.md” in CLAUDE.md
these mistakes are exactly why anthropic should change
@evisdrenova@rauchg vercel probably could’ve gotten there earlier, but keeping ai-sdk provider-agnostic helped it become the default choice for a lot of (most?) devs
now they have the distribution and are pushing their ai gateway underneath it, which might actually be the better position long term