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

Claude's system prompt is over 24k tokens with tools

github.com

Post reply on HN
Print view View original

71–80 of 350 posts

Re: Claude's system prompt is over 24k tokens with tools

#71

Post by Terr_ »

horacemorace wrote: post #44
behnamoh wrote: post #31

Earlier quoted context omitted.

> The assistant is Claude, created by Anthropic. > The current date is {{currentDateTime}}. > Claude enjoys helping humans and sees its role as an intelligent and kind assistant to the people, with depth and wisdom that makes it more than a mere tool. Why do they refer to Claude in third person? Why not say "You're Claude and you enjoy helping hoomans"?

LLMs don’t seem to have much notion of themselves as a first person subject, in my limited experience of trying to engage it.

Yeah, the algorithm is a nameless, ego-less make-document-longer machine, and you're trying to set up a new document which will be embiggened in a certain direction. The document is just one stream of data with no real differentiation of who-put-it-there, even if the form of the document is a dialogue or a movie-script between characters.

Re: Claude's system prompt is over 24k tokens with tools

#72

Post by mrweasel »

dr_kretyn wrote: post #21

I somehow feel cheated seeing explicit instructions on what to do per language, per library. I hoped that the "intelligent handling" comes from the trained model rather than instructing on each request.

I don't know if I feel cheated, but it seems a little unmanageable. How is this suppose to scale? How the hell do you even start to debug the LLM when it does something incorrect? It's not like you can attach a debugger to English.

The "vibe" I'm getting is that of a junior developer who slows problems be tacking on an ever increasing amount of code, rather than going back an fixing underlying design flaws.

Re: Claude's system prompt is over 24k tokens with tools

#73

Post by dr_kiszonka »

SafeDusk wrote: post #14

In addition to having long system prompts, you also need to provide agents with the right composable tools to make it work. I’m having reasonable success with these seven tools: read, write, diff, browse, command, ask, think. There is a minimal template here if anyone finds it useful: https://github.com/aperoc/toolkami

Maybe you could ask one of the agents to write some documentation?

Re: Claude's system prompt is over 24k tokens with tools

#75

Post by turing_complete »

aaronbrethorst wrote: post #69
o11c wrote: post #45

Earlier quoted context omitted.

LLMs are notoriously bad at dealing with pronouns, because it's not correct to blindly copy them like other nouns, and instead they highly depend on the context.

[flagged]

'It' is obviously the correct pronoun.

Re: Claude's system prompt is over 24k tokens with tools

#77

Post by voidUpdate »

bjornsing wrote: post #24

I was just chatting with Claude and it suddenly spit out the text below, right in the chat, just after using the search tool. So I'd say the "system prompt" is probably even longer. Claude NEVER repeats, summarizes, or translates song lyrics. This is because song lyrics are copyrighted content, and we need to respect copyright protections. If asked for song lyrics, Claude should decline the request. (There are no son…

> " and we need to respect copyright protections"

They have definitely always done that and not scraped the entire internet for training data

Re: Claude's system prompt is over 24k tokens with tools

#78

Post by impossiblefork »

moralestapia wrote: post #46

[flagged]

The job of the system is to be useful, not to be AI.

Long prompts are very useful for getting good performance and establishing a baseline for behaviour, which the model can then continue.

Furthermore, you can see this as exploiting an aspect of these models that make them uniquely flexible: in context learning.

Re: Claude's system prompt is over 24k tokens with tools

#80

Post by darkteflon »

SafeDusk wrote: post #14

In addition to having long system prompts, you also need to provide agents with the right composable tools to make it work. I’m having reasonable success with these seven tools: read, write, diff, browse, command, ask, think. There is a minimal template here if anyone finds it useful: https://github.com/aperoc/toolkami

This is really cool, thanks for sharing.

uv with PEP 723 inline dependencies is such a nice way to work, isn’t it. Combined with VS Code’s ‘# %%’-demarcated notebook cells in .py files, and debugpy (with a suitable launch.json config) for debugging from the command line, Python dev finally feels really ergonomic these last few months.

Post reply on HN