[mrlnstk]

But will this be released as a feature? For me it seems like it's an Anthropic internal tool to secretly contribute to public repositories to test new models etc.

[BoppreH]

I don't care who is using it, I don't want LLMs pretending to be humans in public repos. Anthropic just lost some points with me for this one.

EDIT: I just realized this might be used without publishing the changes, for internal evaluation only as you mentioned. That would be a lot better.

[bhaak]

A benign use of this mode is developing on their own public repositories.

https://github.com/anthropics/claude-code