News for hackers. Stuff that matters.

lusob

Author here. I’ve been running this experiment for a couple of years whenever a new model comes out, and this is the first time the results have been good enough to share.

I provide an LLM with a natural language specification (e.g., "an HTTP server on port 8125"), and a bash loop executes what the model generates; the actual error encountered is then fed back to the model until the test passes. There are three levels: C with gcc, assembly with as + ld, and raw bytes (where the model writes the ELF file directly, with nothing between it and the binary other than `xxd -r`).

The raw bytes level isn't always reliable: in 5 runs using Claude Sonnet 5.5 on x86-64, "Hello, World" succeeded in 4 out of 5 attempts, and the HTTP server in 2 out of 5. The C and assembly levels succeeded in all 5 attempts. The system also executes binaries generated by the model, so please check what the code does before running it.

I’d be happy to answer any questions

Show HN: Neural window manager, neural network moving windows from mouse actions

https://lusob.github.io/neural-os/

I'd been mulling over this crazy idea for a while. Can programs be generated? Inspired by recent advances in world models, I wondered if we could do away with source code and generate pixels directly and interactively.As an experiment to answer this, I set out to create a neural window manager, training a neural network to predict what the screen would look like next.Basically, the idea was...

( Read More... | 1 comment | 3 points | on HN )
Re:ChatGPT Code Reviewer on Monday May 22, 2023 @08:20AM (#36030465)
This is a Python program that uses OpenAI's ChatGPT to generate code review comments from diffs. The program reads the diff changes from the standard input, which allows piping from git diffs (or any other diff tool) directly into the program.
git diff master..branch | python3 chatgpt_code_reviewer.py
Hi! the primary function of the mAIker is to generate code based on a prompt, rather than debugging existing code. However, it could be a good idea to add to the roadmap, thanks!
Have you ever wished you could generate a complete code project from a single sentence? Now you can, thanks to mAIker, the latest VSCode extension powered by OpenAI api.

With MAIker, all you have to do is enter a simple prompt, such as "build a space invaders game in js and html", and watch as the extension generates a fully-functional codebase that meets your requirements. MAIker uses advanced algorithms to analyze your prompt and select the most appropriate frameworks, libraries, and coding patterns to create a project that is efficient, maintainable, and scalable.

Whether you're a seasoned developer looking to save time on repetitive tasks or a beginner who wants to learn how to code by example, MAIker is the ultimate tool for boosting your productivity and creativity.

Give it a try today and experience the power of AI at your fingertips.

Maiker is a VSCode extension to generates coding projects from on a user prompt using OpenAI ChatGPT api
Maiker is a VSCode extension to generates coding projects from on a user prompt using OpenAI ChatGPT api

Older »