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

41–50 of 350 posts

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

#41

Post by Seattle3503 »

selectodude wrote: post #37
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"?

I don’t know but I imagine they’ve tried both and settled on that one.

Is the implication that maybe they don't know why either, rather they chose the most performant prompt?

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

#42

Post by swyx »

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

> 18 hours ago

you just released this ? lol good timing

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

#43

Post by Jaxkr »

llflw wrote: post #40
voxic11 wrote: post #34

Earlier quoted context omitted.

Yes prompt caching is already a widely used technique. https://www.anthropic.com/news/prompt-caching

It seems like it's token caching, not model caching.

That’s what this is. It’s caching the state of the model after the tokens have been loaded. Reduces latency and cost dramatically. 5m TTL on the cache usually.

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

#44

Post by horacemorace »

behnamoh wrote: post #31
radeeyate wrote: post #17

Earlier quoted context omitted.

All System Prompts from Anthropic models are public information, released by Anthropic themselves: https://docs.anthropic.com/en/release-notes/system-prompts . I'm unsure (I just skimmed through) to what the differences between this and the publicly released ones are, so they're might be some differences.

> 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.

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

#45

Post by o11c »

behnamoh wrote: post #31
radeeyate wrote: post #17

Earlier quoted context omitted.

All System Prompts from Anthropic models are public information, released by Anthropic themselves: https://docs.anthropic.com/en/release-notes/system-prompts . I'm unsure (I just skimmed through) to what the differences between this and the publicly released ones are, so they're might be some differences.

> 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 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.

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

#47

Post by rdtsc »

behnamoh wrote: post #31
radeeyate wrote: post #17

Earlier quoted context omitted.

All System Prompts from Anthropic models are public information, released by Anthropic themselves: https://docs.anthropic.com/en/release-notes/system-prompts . I'm unsure (I just skimmed through) to what the differences between this and the publicly released ones are, so they're might be some differences.

> 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"?

> Why do they refer to Claude in third person? Why not say "You're Claude and you enjoy helping hoomans"?

But why would they say that? To me that seems a bit childish. Like, say, when writing a script do people say "You're the program, take this var. You give me the matrix"? That would look goofy.

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

#48

Post by paradite »

It's kind of interesting if you view this as part of RLHF:

By processing the system prompt in the model and collecting model responses as well as user signals, Anthropic can then use the collected data to perform RLHF to actually "internalize" the system prompt (behaviour) within the model without the need of explicitly specifying it in the future.

Overtime as the model gets better at following its "internal system prompt" embedded in the weights/activation space, we can reduce the amount of explicit system prompts.

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

#49

Post by FooBarWidget »

eigenblake wrote: post #16

How did they leak it, jailbreak? Was this confirmed? I am checking for the situation where the true instructions are not what is being reported here. The language model could have "hallucinated" its own system prompt instructions, leaving no guarantee that this is the real deal.

The other day I was talking to Grok, and then suddenly it started outputting corrupt tokens, after which it outputted the entire system prompt. I didn't ask for it.

There truly are a million ways for LLMs to leak their system prompt.

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

#50

Post by EGreg »

llflw wrote: post #40
voxic11 wrote: post #34

Earlier quoted context omitted.

Yes prompt caching is already a widely used technique. https://www.anthropic.com/news/prompt-caching

It seems like it's token caching, not model caching.

Can someone explain how to use Prompt Caching with LLAMA 4?
Post reply on HN