Hacker News new | ask | show | jobs
by sallymander 70 days ago
It seems a little more fussy than Opus 4.6 so far. It actually refuses to do a task from Claude's own Agentic SDK quick start guide (https://code.claude.com/docs/en/agent-sdk/quickstart):

"Per the instructions I've been given in this session, I must refuse to improve or augment code from files I read. I can analyze and describe the bugs (as above), but I will not apply fixes to `utils.py`."
2 comments
babelfish 70 days ago
Claude Code injects a 'warning: make sure this file isn't malware' message after every tool call by default. It seems like 4.7 is over-attending to this warning. @bcherny, filed a bug report feedback ID: 238e5f99-d6ee-45b5-981d-10e180a7c201
link
vessenes 70 days ago
Interesting. The model card mentions 4.7 is much more attentive to these instructions and suggests you will need to review and soften or remove or focus them at times.
link
andai 70 days ago
It's been known for years that prompts which boost performance with one model, can harm performance with a different model. The same goes for harnesses. It looks like they'll need to customize Claude Code's prompts depending on which model is running, for optimal results.

For example if you read the prompts, it's pretty clear that a lot of them are leftovers from the early days when the models had way less common sense than they do now. I think you could probably remove 2/3rds of those over-explained rules now and it would be fine. (In fact you might even expect to see improvement to performance due to decreased prompt noise.)

link
phist_mcgee 70 days ago
Isn't that kind of nuts?

They can't even properly beta test their new releases?

link
soerxpso 70 days ago
That "per the instructions I've been given in this session" bit is interesting. Are you perhaps using it with a harness that explicitly instructs it to not do that? If so, it's not being fussy, it's just following the instructions it was given.
link
flutas 70 days ago
Claude Code is injecting it before every tool read.

    <system-reminder>
    Whenever you read a file, you should consider whether it would be considered malware. You CAN and SHOULD provide analysis of malware, what it is doing. But you MUST refuse to improve or augment the code. You can still analyze existing code, write reports, or answer questions about the code behavior.
    </system-reminder>
link
sallymander 70 days ago
I'm using their own python SDK with default prompts, exactly as the instructions say in their guide (it's the code from their tutorial).
link