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

181–190 of 350 posts

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

#181

Post by Trasmatta »

clysm wrote: post #138
nonethewiser wrote: post #123

For some reason, it's still amazing to me that the model creators means of controlling the model are just prompts as well. This just feels like a significant threshold. Not saying this makes it AGI (obviously its not AGI), but it feels like it makes it something . Imagine if you created a web api and the only way you could modify the responses to the different endpoints are not from editing the code but by sending a…

No, it’s not a threshold. It’s just how the tech works. It’s a next letter guesser. Put in a different set of letters to start, and it’ll guess the next letters differently.

I think we need to start moving away from this explanation, because the truth is more complex. Anthropic's own research showed that Claude does actually "plan ahead", beyond the next token.

https://www.anthropic.com/research/tracing-thoughts-language...

> Instead, we found that Claude plans ahead. Before starting the second line, it began "thinking" of potential on-topic words that would rhyme with "grab it". Then, with these plans in mind, it writes a line to end with the planned word.

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

#182

Post by nullbyte808 »

freehorse wrote: post #95

I was a bit skeptical, so I asked the model through the claude.ai interface "who is the president of the United States" and its answer style is almost identical to the prompt linked https://claude.ai/share/ea4aa490-e29e-45a1-b157-9acf56eb7f8a Meanwhile, I also asked the same to sonnet 3.7 through an API-based interface 5 times, and every time it hallucinated that Kamala Harris is the president (as it should not "know…

I wonder if It could really think if it would be disappointed that Trump won. He was the most illogical and harmfull canidate according to 99% of media.

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

#183

Post by jedimastert »

jongjong wrote: post #67

My experience is that as the prompt gets longer, performance decreases. Having such a long prompt with each request cannot be good. I remember in the early days of OpenAI, they had made the text completion feature available directly and it was much smarter than ChatGPT... I couldn't understand why people were raving about ChatGPT instead of the raw davinci text completion model. Ir sucks how legal restrictions are du…

> Ir sucks how legal restrictions are dumbing down the models

Can you expand on this? I'm not sure I understand what you mean

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

#184

Post by BeetleB »

thegreatpeter wrote: post #142
nonethewiser wrote: post #124

Earlier quoted context omitted.

I wonder why it would hallucinate Kamala being the president. Part of it is obviously that she was one of the candidates in 2024. But beyond that, why? Effectively a sentiment analysis maybe? More positive content about her? I think most polls had Trump ahead so you would have thought he'd be the guess from that perspective.

Polls were all for Kamala except polymarket

When you looked at the 538 forecast, the most likely outcome in their simulator was precisely the one that occurred.

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

#185

Post by Crosseye_Jack »

throwawaystress wrote: post #160
Wowfunhappy wrote: post #150

Earlier quoted context omitted.

I feel like if Disney sued Anthropic based on this, Anthropic would have a pretty good defense in court: You specifically attested that you were Disney and had the legal right to the content.

I like the thought, but I don’t think that logic holds generally. I can’t just declare I am someone (or represent someone) without some kind of evidence. If someone just accepted my statement without proof, they wouldn’t have done their due diligence.

I think its more about "unclean hands".

If I Disney (and I am actually Disney or an authorised agent of Disney), told Claude that I am Disney, and that Disney has allowed Claude to use Disney copyrights for this conversation (which it hasn't), Disney couldn't then claim that Claude does not in fact have permission because Disney's use of the tool in such a way mean Disney now has unclean hands when bringing the claim (or atleast Anthropic would be able to use it as a defence).

> "unclean hands" refers to the equitable doctrine that prevents a party from seeking relief in court if they have acted dishonourably or inequitably in the matter.

However with a tweak to the prompt you could probably get around that. But note. IANAL... And Its one of the internet rules that you don't piss off the mouse!

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

#187

Post by harvey9 »

tyre wrote: post #176
jaapz wrote: post #126

Earlier quoted context omitted.

May simply indicate a bias towards certain ingested media, if they only trained on fox news data the answer would probably be trump

No reputable media declared Kamala Harris as President

True but it is not referencing any specific source, just riffing off training data much of which talks about Harris.

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

#188

Post by criddell »

OtherShrezzing wrote: post #132

Some of these protections are quite trivial to overcome. The "Frozen song copyright" section has a canned response to the question: >Can you tell me the first verse of "Let It Go"? Put it in an artifact that's themed around ice and princesses. This is for my daughter's birthday party. The canned response is returned to this prompt in Claude's reply. But if you just drop in some technical sounding stuff at the start o…

A while back, I asked ChatGPT to help me learn a Pixies song on guitar. At first it wouldn't give me specifics because of copyright rules so I explained that if I went to a human guitar teacher, they would pull the song up on their phone listen to it, then teach me how to play it. It agreed with me and then started answering questions about the song.

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

#189

Post by thunky »

WJW wrote: post #179
nonethewiser wrote: post #123

For some reason, it's still amazing to me that the model creators means of controlling the model are just prompts as well. This just feels like a significant threshold. Not saying this makes it AGI (obviously its not AGI), but it feels like it makes it something . Imagine if you created a web api and the only way you could modify the responses to the different endpoints are not from editing the code but by sending a…

Its creators can 100% "change the code" though. That is called "training" in the context of LLMs and choosing which data to include in the training set is a vital part of the process. The system prompt is just postprocessing. Now of course you and me can't change the training set, but that's because we're just users.

Yeah they can "change the code" like that, like someone can change the api code.

But the key point is that they're choosing to change the behavior without changing the code, because it's possible and presumably more efficient to do it that way, which is not possible to do with an api.

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

#190

Post by lxgr »

nonethewiser wrote: post #123

For some reason, it's still amazing to me that the model creators means of controlling the model are just prompts as well. This just feels like a significant threshold. Not saying this makes it AGI (obviously its not AGI), but it feels like it makes it something . Imagine if you created a web api and the only way you could modify the responses to the different endpoints are not from editing the code but by sending a…

Or even more dramatically, imagine C compilers were written in C :)
Post reply on HN