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

Show HN: My LLM CLI tool can run tools now, from Python code or plugins

simonwillison.net

Post reply on HN
Print view View original

41–50 of 178 posts

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#41

Post by bgwalter »

davely wrote: post #21
th0ma5 wrote: post #9

Earlier quoted context omitted.

[flagged]

I work for a tech company you’ve definitely heard of. I use the “llm” tool every single day. You may not know it, and that’s okay, but Simon’s tools are an immense help to tons of developers using LLMs. I know it’s fun and trendy to hate on LLMs, but if you’re not productive with them at this point, you’re either: 1. Working on a novel problem or in some obscure language, or 2. Have a skill issue related to how to ut…

Oh yeah? Where is all this new great software written by the prompt geniuses?

There is none. All they do is steal from real software developers and blog about the half finished garbage they produce and that no one uses.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#45

Post by kristopolous »

It's worth noting the streaming markdown renderer I wrote just for this tool: https://github.com/day50-dev/Streamdown

More background: https://github.com/simonw/llm/issues/12

(Also check out https://github.com/day50-dev/llmehelp which features a tmux tool I built on top of Simon's llm. I use it every day. Really. It's become indispensable)

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#46

Post by simonw »

bgwalter wrote: post #44
simonw wrote: post #43

Earlier quoted context omitted.

Are you an alt for th0ma5?

Are you paid by OpenAI?

No. If I was they'd probably be a bit angry about how much time I spend writing about their competitors:

https://simonwillison.net/tags/anthropic/

https://simonwillison.net/tags/gemini/

https://simonwillison.net/tags/mistral/

https://simonwillison.net/tags/qwen/

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#47

Post by puttycat »

simonw wrote: post #40
puttycat wrote: post #38

Earlier quoted context omitted.

> while minimizing or eliminating JavaScript How come it doesn't know for sure?

Because I only showed it the CSS! It doesn't even get the HTML, it's guessed all of that exclusively from what's in the (uncommented) CSS code. Though it's worth noting that CSS Minecraft was first released three years ago, so there's a chance it has hints about it in the training data already. This is not a meticulous experiment. (I've had a search around though and the most detailed explanation I could find of how…

Thanks. I meant that it should understand that the css doesn't require/relates to a js

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#48

Post by simonw »

kristopolous wrote: post #45

It's worth noting the streaming markdown renderer I wrote just for this tool: https://github.com/day50-dev/Streamdown More background: https://github.com/simonw/llm/issues/12 (Also check out https://github.com/day50-dev/llmehelp which features a tmux tool I built on top of Simon's llm. I use it every day. Really. It's become indispensable)

Wow, that library is looking really great!

I think I want a plugin hook that lets plugins take over the display of content by the tool.

Just filed an issue: https://github.com/simonw/llm/issues/1112

Would love to get your feedback on it, I included a few design options but none of them feel 100% right to me yet.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#49

Post by xrd »

simonw wrote: post #37
stavros wrote: post #36

Have you guys had luck with tool calls? I made a simple assistant with access to my calendar, and most models fail to call the tool to add calendar events. GPT-4.1 also regularly tries to gaslight me into believing that it added the event when it didn't call the tool! Overall, I found tool use extremely hit-and-miss, to the point where I'm sure I'm doing something wrong (I'm using the OpenAI Agents SDK, FWIW).

I get the impression that the key to getting great performance out of tool calls is having a really detailed system prompt, with a bunch of examples. Anthropic's system prompt just for their "web_search" tool is over 6,000 tokens long! https://simonwillison.net/2025/May/25/claude-4-system-prompt...

Is no one else bothered by that way of using tools? Tools feel like a way to get deterministic behavior from a very hallucinatory process. But unless you put a very lengthy and comprehensive non-deterministic English statement, you can't effectively use tools. As we all know, the more code, the more bugs. These long and often hidden prompts seem like the wrong way to go.

And, this is why I'm very excited about this addition to the llm tool, because it feels like it moves the tool closer to the user and reduces the likelihood of the problem I'm describing.

Re: Show HN: My LLM CLI tool can run tools now, from Python code or plugins

#50

Post by kbelder »

tantalor wrote: post #33

This greatly opens up the risk of footguns. The doc [1] warns about prompt injection, but I think a more likely scenario is self-inflicted harm. For instance, you give a tool access to your brokerage account to automate trading. Even without prompt injection, there's nothing preventing the bot from making stupid trades. [1] https://llm.datasette.io/en/stable/tools.html

If you hook an llm up to your brokerage account, someone is being stupid, but it ain't the bot.
Post reply on HN