Not exactly. Every time I ask something using Fable, it switches to Opus. The subjects (and I tried many) seem to be irrelevant.

Basically, I can't use Fable.

▲

0xy 3 hours ago | parent | next [-]

It cannot be used for ANY coding tasks, lol.

https://x.com/AnthropicAI/status/2072163884430229756

▲

usef- 2 hours ago | parent [-]

It can. They meant "some coding tasks". Not "all coding tasks"

▲

cromka 2 hours ago | parent [-]

No, they said some routine tasks "like coding". That logically implies coding is one of the tasks they block.

▲

usef- an hour ago | parent [-]

Anthropic employees clarified: https://x.com/trq212/status/2072185565076988326?s=20

	▲	cromka an hour ago \| parent [-]
		Oh, OK then. Good to hear! Thanks for the link!

▲

LoganDark 4 hours ago | parent | prev [-]

Check your CLAUDE.md, etc. for any of the banned topics or anything adjacent. Also check your recent Git commit history, if you're running the agent in a repository, as well. The classifier trips on anything anywhere in context, so those could be sources of rejections.

▲

iririririr 4 hours ago | parent [-]

adding rules for the agent to ignore version control and never touch git files or commands (except for git log) improve my slop coding 100%. no risk of sneak commits and much less token wasted.

	▲	LoganDark 4 hours ago \| parent [-]
		Claude Code automatically adds some of the most recent git commit messages to the system prompt. This was discovered when having git commit messages containing any OpenClaw information would result in Anthropic billing your extra usage (since they have a vendetta or something)