It still bothers me that almost every agentic TUI is written in TS + React. It often consumes at least a few GB of RAM. No one bothers about it. Everybody is trying to ship as fast as possible.
Well codex is written in rust.
Claude Code 2.0
261–270 of 431 posts
Re: Claude Code 2.0
#262Re: Claude Code 2.0
#263Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…
Instead of containers, which may not always be available, I'm experimenting with having control over the shell to whitelist the commands that the LLM can run [0]. Similar to an allow list, but configured outside the terminal agent. Also trying to make it easy to use the same technique in macOS and Linux [0]: https://ricardoanderegg.com/posts/control-shell-permissions-...
An interesting exercise would be to let a friend into this restricted shell, with a prize for breaking out and running rm -rf / --no-preserve-root. Then you know to switch to something higher-security once LLM capabilities reach the level of that friend.
Re: Claude Code 2.0
#264Earlier quoted context omitted.
I have it master my music. I drop all the stems in a folder, tell it what I want, and off it goes to write a python script specifically for the album. It’s way better than doing it in the DAW, which usually takes me hours (or days in some cases). It can get it to 90% in minutes, only requiring some fine-tuning at the end.
Wow, could you expand on this? What kind of effects can you get out of it? I’m somewhat skeptical that this could even come close to a proper mastering chain, so I’d be extremely interested to learn more :)
Any effect you can imagine. It could probably write a DAW if you wanted it to, but a “one-off” script? Easy. I think the best thing is when I tell it something like “it sounds like there is clipping around the 1:03 mark” it will analyze it, find the sign flip in the processor chain, and apply the fix. It’s much faster at this than me.
Note that there needs to be open source libraries and toolings. It can’t do a Dolby Atmos master, for example. So you still need a DAW.
Re: Claude Code 2.0
#265Re: Claude Code 2.0
#266Earlier quoted context omitted.
They're only as dangerous as the capabilities you give them. I just created a `codex` and `claude` user on my Linux box and practically always run in yolo mode. I've not had a problem so far. Also, I think shellagent sounds cooler.
I tried this but it's incredibly annoying as you'll get a mixture of file ownerships and permissions. Instead I run it in bubblewrap sandbox: https://blog.gpkb.org/posts/ai-agent-sandbox/
This is a really clever solution
Re: Claude Code 2.0
#267It still bothers me that almost every agentic TUI is written in TS + React. It often consumes at least a few GB of RAM. No one bothers about it. Everybody is trying to ship as fast as possible.
Ram is cheap, 99.9% of the audience that would use this are running heavy envs on powerful computers. I can totally understand why they write it that way. Better to have faster iteration and alienate 0.1% of serious users than to slow development just to cater to them.
Re: Claude Code 2.0
#268Re: Claude Code 2.0
#269Tangential, did anybody get FOMO about Aider and found a much better tool?
I was using aider quite a lot from ~ 7 months ago to ~ 3 months ago. I had to stop because they refuse to implement MCPs and Claude/Codex style agentic workflow just yields better results.
Have you tried Aider-desk? (https://github.com/hotovo/aider-desk)
I haven’t fully tested it yet, but I found it because its supports JetBrains IDE integration. It has MCPs as well.
Re: Claude Code 2.0
#270Earlier quoted context omitted.
Cursor will pivot to a computer use company. The gap between coding agents in your terminal and computer agents that work on your entire operating system is just too narrow and will be crossed over quick.
Once this tech is eliminating jobs on a massive scale I'll believe the AI hype. Not to say that couldn't be right around the corner - I have no clue. But being able to perform even just data entry tasks with better-than-human accuracy would be a huge deal.
That’s the risk - a lot of people suddenly flipping their beliefs at once, especially they’re the same people who are losing the jobs. It’s a civil unrest scenario.