81–90 of 178 posts
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
Every time I update llm I have to reinstall all plugins, like gemini and ollama. My Gemini key is still saved, as are my aliases for my ollama models, so I don't get why the installed plugins are lost.
I was running into this too until I started upgrading with llm install -U llm instead of uv tool upgrade llm (the latter of which is recommended by simonw in the original post)
Earlier quoted context omitted.
They are not. I think it is a good criticism though. Many people seem to be touting productivity that is only in the context of productivity towards more LLM inference operations and not productive in the sense of solving real world computing problems. There is a lot of material that suggests positive results are a kind of wish casting and people are not aware of the agency they are bringing to the interaction. The f…
No one is happy about the need for prompt engineering and other LLM hacks, but part of being a professional in the real world is doing what works.
This is just a new fad like agile, where the process and tool obsessed developers blog and preach endlessly without delivering any results.
For them "it works". The rest of us can either join the latest madness or avoid places that use LLMs, which of course includes all open source projects that do actual work that is not measured in GitHub kLOCs and marketing speak.
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)
This one is a ZSH plugin that uses zle to translate your English to shell commands with a keystroke.
https://github.com/day50-dev/Zummoner
It's been life changing for me. Here's one I wrote today:
$ git find out if abcdefg is a descendent of hijklmnop
$ for i in $(seq 1 6); do
printf "%${i}sh${i}\n\n-----\n" | tr " " "#";
done | pv -bqL 30
$ for i in $(seq 1 6); do
printf "(# $i times)\n\n-----\n"
done | pv (30 bps and quietly)
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
Any tool can be misused
Letting the LLM run the tool unsupervised is another thing entirely. We do not understand the choices the machines are making. They are unpredictable and you can't root-cause their decisions.
LLM tool use is a new thing we haven't had before, which means tool misuse is a whole new class of FUBAR waiting to happen.
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)
Also I forgot to one other built on llm. This one is a ZSH plugin that uses zle to translate your English to shell commands with a keystroke. https://github.com/day50-dev/Zummoner It's been life changing for me. Here's one I wrote today: $ git find out if abcdefg is a descendent of hijklmnop In fact I used it in one of these comments $ for i in $(seq 1 6); do printf "%${i}sh${i}\n\n-----\n" | tr " " "#"; done | pv -b…
It's also intelligent about inferring leading zeros without needing to be told with options, e.g. {001..995}.
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
[flagged]
https://news.ycombinator.com/item?id=44073456
https://news.ycombinator.com/item?id=44073413
https://news.ycombinator.com/item?id=44070923
https://news.ycombinator.com/item?id=44070514
https://news.ycombinator.com/item?id=44010921
https://news.ycombinator.com/item?id=43970274
If you wouldn't mind reviewing https://news.ycombinator.com/newsguidelines.html and taking the intended spirit of the site more to heart, we'd be grateful.
Earlier quoted context omitted.
Can we have some guidance about how to call out bullshit? That's right in the site docs linked above which you should check out.
I guess I'll need clarification -- getting trapped in a non-productive quagmire is the experience of a lot of people. The author chooses when to use terms in different contexts to get out of arguments ... and also, we still don't have any good way to test these things, so I'm not sure where I'm running afoul of the rules when it seems like everyone else is.
Earlier quoted context omitted.
If you hook an llm up to your brokerage account, someone is being stupid, but it ain't the bot.
You think "senior leadership/boards of directors" aren't thinking of going all in with AI to "save money" and "grow faster and cheaper"? This is absolutely going to happen at a large scale and then we'll have "cautionary tales" and a lot of "compliance" rules.
Fortunately this gets me 90% of the way there:
llm -f README.md -f llm.plugin.zsh -f completions/_llm -f https://simonwillison.net/2025/May/27/llm-tools/ "implement tab completions for the new tool plugins feature"
My repo is here:
https://github.com/eliyastein/llm-zsh-plugin
And again, it's a bit of a mess, because I'm trying to get as many options and their flags as I can. I wouldn't mind if anyone has any feedback for me.