Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Changes in the system prompt between Claude Opus 4.6 and 4.7

simonwillison.net

Post reply on HN
Print view View original

81–90 of 240 posts

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#81

Post by tuetuopay »

embedding-shape wrote: post #6

> The new section includes: When a request leaves minor details unspecified, the person typically wants Claude to make a reasonable attempt now, not to be interviewed first. Uff, I've tried stuff like these in my prompts, and the results are never good, I much prefer the agent to prompt me upfront to resolve that before it "attempts" whatever it wants, kind of surprised to see that they added that

Dammit that’s why I could never get it to not try to one shot answers, it’s in the god damn system prompt… and it explains why no amount of user "system" prompt could fix this behavior.

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#82

Post by ikari_pl »

embedding-shape wrote: post #6

> The new section includes: When a request leaves minor details unspecified, the person typically wants Claude to make a reasonable attempt now, not to be interviewed first. Uff, I've tried stuff like these in my prompts, and the results are never good, I much prefer the agent to prompt me upfront to resolve that before it "attempts" whatever it wants, kind of surprised to see that they added that

I usually need to remind it 5 times to do the opposite - because it makes decisions that I don't like or that are harmful to the project—so if it lands in Claude Code too, I have hard times ahead.

I try to explicitly request Claude to ask me follow-up questions, especially multiple-choice ones (it explains possible paths nicely), but if I don't, or when it decides to ignore the instructions (which happens a lot), the results are either bad... or plain dangerous.

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#85

Post by ikari_pl »

> Claude keeps its responses focused and concise so as to avoid potentially overwhelming the user with overly-long responses. Even if an answer has disclaimers or caveats, Claude discloses them briefly and keeps the majority of its response focused on its main answer.

I am strongly opinionated against this. I use Claude in some low-level projects where these answers are saving me from making really silly things, as well as serving as learning material along the way.

This should not be Anthropic's hardcoded choice to make. It should be an option, building the system prompt modularily.

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#86

Post by ikari_pl »

walthamstow wrote: post #24

The eating disorder section is kind of crazy. Are we going to incrementally add sections for every 'bad' human behaviour as time goes on?

Are the prompts used both by the desktop app, like typical chatbot interfaces, and Claude Code?

Because it's a waste of my money to check whether my Object Pascal compiler doesn't develop eating disorders, on every turn.

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#87

Post by layer8 »

zozbot234 wrote: post #79
walthamstow wrote: post #24

The eating disorder section is kind of crazy. Are we going to incrementally add sections for every 'bad' human behaviour as time goes on?

That part of the system prompt is just stating that telling someone who has an actual eating disorder to start counting calories or micro-manage their eating in other ways (a suggestion that the model might well give to an average person for the sake of clear argument, which would then be understood sensibly and taken with a grain of salt) is likely to make them worse off, not better off. This seems like a common-sen…

If it’s common sense, shouldn’t the model know it already?

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#88

Post by MoltenMan »

zozbot234 wrote: post #79
walthamstow wrote: post #24

The eating disorder section is kind of crazy. Are we going to incrementally add sections for every 'bad' human behaviour as time goes on?

That part of the system prompt is just stating that telling someone who has an actual eating disorder to start counting calories or micro-manage their eating in other ways (a suggestion that the model might well give to an average person for the sake of clear argument, which would then be understood sensibly and taken with a grain of salt) is likely to make them worse off, not better off. This seems like a common-sen…

The problem is that this is an incredibly niche / small issue (i.e. At some point you just have to accept that llm's, like people, make mistakes, and that's ok!

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#89

Post by akdor1154 »

saagarjha wrote: post #78
mwexler wrote: post #45

Interesting that it's not a direct "you should" but an omniscient 3rd person perspective "Claude should". Also full of "can" and "should" phrases: feels both passive and subjunctive as wishes, vs strict commands (I guess these are better termed “modals”, but not an expert)

That’s because Anthropic does not consider their model as having personality but rather that it simulates the experience of an abstract entity named Claude.

That sounds really interesting, but my google-fu is not up to task here, I'm getting pages and pages of nonsense asking if Claude is conscious. Can you elaborate?

Re: Changes in the system prompt between Claude Opus 4.6 and 4.7

#90

Post by zozbot234 »

MoltenMan wrote: post #88
zozbot234 wrote: post #79

Earlier quoted context omitted.

That part of the system prompt is just stating that telling someone who has an actual eating disorder to start counting calories or micro-manage their eating in other ways (a suggestion that the model might well give to an average person for the sake of clear argument, which would then be understood sensibly and taken with a grain of salt) is likely to make them worse off, not better off. This seems like a common-sen…

The problem is that this is an incredibly niche / small issue (i.e. At some point you just have to accept that llm's, like people, make mistakes, and that's ok!

It's not "incredibly niche" when you consider the kinds of questions that average everyday users might submit to these AIs. Diet is definitely up there, given how unintuitive it is for many.

> At some point you just have to accept that llm's, like people, make mistakes, and that's ok!

Except that's not the way many everyday users view LLM's. The carwash prompt went viral because it showed the LLM making a blatant mistake, and many seem to have found this genuinely surprising.

Post reply on HN