alt Hacker NewsI've been largely disappointed how much the Claude models ignore custom instructions, and sometimes even prompts on the chat interface. It sometimes feels like talking to a wall, or as if there was a third person in the chatroom whose messages I can't see.
I can't help but feel this is intentional towards the 'Agentic' workflow.
Replies
I think this seems purposeful, as there's 2 opposing forces at play: - Have a model that follows the users instructions - Have a model that follows the system prompt instructions more
For the 'safety' argument (Re: Fable), they need these models to have basically a 2-tier instruction system, but given LLMs aren't great with actual Logic unless they program it out to test, this runs afoul and we get one or the other.
Feels like optimizing for either precision or recall, but can't have both
Totally agreed. I sometimes wonder if they are making the model "lazy" with each iteration, it keeps getting better at avoiding work.
> or as if there was a third person in the chatroom whose messages I can't see.
If you set off a classifier, that's how it looks to Claude.
Try to run your prompts through Claude to pinpoint any ambiguous parts that can be interpreted in multiple ways, or self-contradictory sections. I typically resolve any prompt-ignoring issues with that.
[dead]
I keep adding selected cases of CLAUDE.md instructions non-compliance reported on claude-code github to that issue https://github.com/anthropics/claude-code/issues/13689. Subjectively the amount of such cases seems lower during the past month. It may be that claude-opus-4-8 (default thinking) is a bit better at instructions following than past models.