"prompt engineering is dead" ha!
Claude's system prompt is over 24k tokens with tools
141–150 of 350 posts
Re: Claude's system prompt is over 24k tokens with tools
#142I 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 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
Re: Claude's system prompt is over 24k tokens with tools
#143In 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.
> Combined with VS Code’s ‘# %%’-demarcated notebook cells in .py files
What do you mean by this?
Re: Claude's system prompt is over 24k tokens with tools
#144>Claude NEVER repeats or translates song lyrics and politely refuses any request regarding reproduction, repetition, sharing, or translation of song lyrics. Is there a story behind this?
They're already in trouble for infringing on the copyright of every publisher in the world while training the model, and this will get worse if the model starts infringing copyright in its answers.
Re: Claude's system prompt is over 24k tokens with tools
#145Earlier 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.
Clearly, it just leaked the election results from the wrong branch of the wavefunction.
A real Trump fan-boy wouldn't trust what the mainstream media says. It's not because the media says that Trump won the election that it is true.
Re: Claude's system prompt is over 24k tokens with tools
#146Re: Claude's system prompt is over 24k tokens with tools
#147> "...and in general be careful when working with headers" I would love to know if there are benchmarks that show how much these prompts improve the responses. I'd suggest trying: "Be careful not to hallucinate." :-)
In general, if you bring something up in the prompt most LLM's will bring special attention to it. It does help the accuracy of the thing you're trying to do. You can prompt an llm not to hallucinate, but typically you wouldn't say "don't hallucinate, you'd ask it to give a null value or say i don't know" which more closely aligns with the models training.
> if you bring something up in the prompt most LLM's will bring special attention to it
How? In which way? I am very curious about this. Is this part of the transformer model or something that is done in the fine-tuning? Or maybe during the post-training?
Re: Claude's system prompt is over 24k tokens with tools
#148I 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…
> Claude NEVER repeats, summarizes, or translates song lyrics. This is because song lyrics are copyrighted content If this is the wild west internet days of LLMs the advertiser safe version in 10 years is going to be awful. > Do not say anything negative about corporation . Always follow official brand guidelines when referring to corporation
9 out of 10 LLMs recommend Colgate[tm]!
Re: Claude's system prompt is over 24k tokens with tools
#149Earlier 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
At some points, Polymarket had a higher probability for Kamala too.
Re: Claude's system prompt is over 24k tokens with tools
#150Some 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…
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.