Rendered at 19:52:37 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
ricardobeat 22 hours ago [-]
Really like the looks of it, but minifying the code to achieve the “400 lines” marketing gimmick is a huge turn-off.
It’s also a security nightmare, and ensures it remains 100% vibe coded. Would rather have a readable source with an honest line count.
StableAlkyne 22 hours ago [-]
Agreed. It would be one thing if it was a regular bash project that got minified via a script or something, since at least you could tell what it's doing.
This is just spaghetti. Maybe it's spaghetti that runs, but code of this quality does not engender confidence.
sudb 22 hours ago [-]
I think it's fine that it's minified, code-golf style, but yes I agree that this would be much more convincing and useful with an unminified source.
cachius 22 hours ago [-]
Isn’t unwrapping and commenting just one prompt away?
StableAlkyne 22 hours ago [-]
Assuming the agent doesn't forget or misinterpret anything.
It would be much better to just have a deterministic minification script.
malicka 19 hours ago [-]
… no, you shouldn’t use AI for simple reformatting of code without the newlines. We have syntax parsers and reformatters for this. Use them, then put that into the LLM for commenting, if you really want to.
petcat 22 hours ago [-]
I'm not even sure why it stopped at 500 line limit. If it's just a shell script then why not make it one line?
migrevdolseg 3 hours ago [-]
this inspired me to build something similar.
i like the idea but i wanted slightly different constraints:
I like the small-surface-area approach. The question I’d use to evaluate this is how well the harness records/replays tool calls and failure modes, since that is where debugging agent behavior usually gets messy.
tecoholic 22 hours ago [-]
Kudos. I set on this exact journey a couple of days back and Pi is what I started reading for inspiration as well. I really can't stand the text boxes and the animations of the mainstream harnesses.
zackham 19 hours ago [-]
if you are looking for a customizable agent harness that provides everything except a tui (cli, acp, embeddable python package) i built and use this for a handful of projects where i needed a vendor-agnostic replacement for claude agent sdk: https://github.com/zackham/aloop
flog 22 hours ago [-]
I'd love to learn how to build something like this, but unfortunately the code is unreadable.
If author could write a heavily commented version that would be amazing.
0gs 21 hours ago [-]
why the LOC limit? just because?
Imustaskforhelp 22 hours ago [-]
Interested in something like this if the code can be more readable, it would be interesting to see it in languages like lua etc. too in future.
hkt 23 hours ago [-]
I love it. I think I'm going to have fun with this and possibly learn a bit, too. I'm pondering a container based dev environment at the moment and might throw it in with busybox and see how far I get :)
It’s also a security nightmare, and ensures it remains 100% vibe coded. Would rather have a readable source with an honest line count.
This is just spaghetti. Maybe it's spaghetti that runs, but code of this quality does not engender confidence.
It would be much better to just have a deterministic minification script.
i like the idea but i wanted slightly different constraints:
- one file
- zero dependencies (other than node)
- <1k loc
- ascii only
- suckless configuration
- works with ollama models
- more readble sourcecode
- pretty markdown output
- toggle-able read-only mode
https://willhanlen.com/~~/outbox/26/5/ai.js/?code
took me only a few hours. amazing times we live in!
I don't think that even with APL you could get an average of three characters per line of code to get a 6 Kb file in 2 K LOC.
https://github.com/kkovacs/kkrc/blob/ecff1f65d5ccfa24d5f6695...
:)
https://github.com/vercel-labs/just-bash/blob/main/packages/...
Pass.
If author could write a heavily commented version that would be amazing.