this post was submitted on 01 Apr 2026
42 points (97.7% liked)

LocalLLaMA

4491 readers
52 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] WhiteRice@lemmy.ml 6 points 16 hours ago (2 children)

It has also been rewritten in python, due to copyright issues.

https://github.com/instructkr/claw-code

[–] GenderNeutralBro 3 points 15 hours ago (1 children)

They say this was done with Codex and OpenCode.

I admit I'm behind the time with AI coding agents. Is it actually possible to do that effectively in such a short time? Or is this going to be riddled with sloppy bugs?

[–] WhiteRice@lemmy.ml 3 points 13 hours ago* (last edited 13 hours ago)

I would say recompiling code with discrete units tests is probably a good use case. It allows for a tight feedback loop with the agent.

You will probably get the mean deliverable. Not industrial unless you think to bake in the requirements.

[–] Canuck@sh.itjust.works 2 points 16 hours ago* (last edited 16 hours ago)

Yes, I posted that one and also another one in my original description if you're interested; it has a full breakdown of the original source code