chmod with extra steps
Just-bash: Bash for Agents
71–78 of 78 posts
Re: Just-bash: Bash for Agents
#72Earlier quoted context omitted.
Agents really do not care at all how "nice" a language is. You only need to be picky with language if a human is going to be working with the code. I get the impression that is not the use case here though
> Agents really do not care at all how "nice" a language is. People do care. > You only need to be picky with language if a human is going to be working with the code. Sooner or later humans will have to work with the code - if only for their own self-preservation. > I get the impression that is not the use case here though If that's not the use case, there's no legitimate use case at all.
I might have misinterpreted what the submitted link is offering then. I thought this was some "secure" sandboxing thing where agents can write ephemeral scripts as tool calls to take arbitrary actions. No human will be looking at that. It's not checked into a repo and is not maintained.
One-off throwaway scripts can be written in literally anything. It does not matter.
Re: Just-bash: Bash for Agents
#73Earlier quoted context omitted.
If you present most LLM's with a run_python tool it won't realize that it can access a standard Linux userspace with it even if it's explicitly detailed. But spiritually the same tool called run_shell it will use correctly. Gotta work with what's in the training data I suppose.
There are a lot of shellscripts holding this world together out there.
don't forget Perl!
Re: Just-bash: Bash for Agents
#74https://github.com/vercel-labs/just-bash/blob/main/src/spec-... That's a lot of incompatibilities. LLMs like to use the shell because it's stable and virtually unchanged for decades. It doesn't need to worry much about versions or whether something is supported or not, it can just assume it is. Re-implementing bash is a herculean effort. I wish good luck.
I would not over-read into that doc. In practice, the only missing stuff are extreme edge cases of the type that is actually not consistent between other implementations of bash. In practice it works great. I haven't seen a failed command in a while [Disclaimer: I made the thing]
I gave it a shot. Failed with a simple `> /dev/null` redirection. LLMs do that a lot.
Good luck with the project! I'm sure it will get there.
Re: Just-bash: Bash for Agents
#75At this point why not make the agents use a restricted subset of python, typescript or lua or something. Bash has been unchanged for decades but its not a very nice language. I know pydantic has been experimenting with https://github.com/pydantic/monty (restricted python) and I think Cloudflare and co were experimenting with giving typescript to agents.
Agents really do not care at all how "nice" a language is. You only need to be picky with language if a human is going to be working with the code. I get the impression that is not the use case here though
Humans will eventually have to work with the code, generally at 3am with alarms going off and three tiers of bosses yelling at them on the phone
Re: Just-bash: Bash for Agents
#76Earlier quoted context omitted.
Before, you said: > they use it because there's a lot of training material. Now, you say: > they are not trying to re-use existing bash code. Can't you see how this is a contradiction? --- I'm sorry, I can't continue like this. I want to have meaningful conversations.
Is English your second language? "They" refers to very different things here.
The issue here is not language, is basic understanding of how LLMs are trained, how agents act on that training and what is the role of the shell from a systems perspective.
I can't have a meaningful conversation with someone that doesn't fully grasp those, no matter in which language.
Re: Just-bash: Bash for Agents
#77I'm hacking on a similar thing that lets you build CLIs directly into xterm / ghostty web so that they also work in the terminal. Eg they are cross platform web and CLI.
Demo: https://wizard-nine-blush.vercel.app/
Project: https://ink-web.dev
I love the approach of just bash as well. Super cool!
Edit: warning - don't use it mobile.
Re: Just-bash: Bash for Agents
#78The unix commandline tools being the most efficient way to use an LLM has been a surprise. I wonder the reason. Maybe 'do one thing well'? The piping? The fact that the tools have been around so long so there are so many examples in the training data? Simplicity? All of it? The success of this project depends on the answer. Even so, I suspect that something like this will be a far too leaky abstraction. But Vercel mu…
> The unix commandline tools being the most efficient way to use an LLM has been a surprise.
> I wonder the reason.
Because they are really, really well designed for humans.
Everyone is trying to reinvent the wheel and create "agent interfaces", but there is fundamentally no difference between what makes a text based interface easy for a human to use and what makes it easy for an agent to use.