kirby88
Joined 5 years ago
Karma
3
Submissions
12
Member since
Apr 20
Recent submissions
Comment · 6 months ago
Claude code is closed source as well (at least before the leak). But point taken thank you.
Comment · 6 months ago
Using a virtual filesystem to minify source code and let the LLM evolve in the minified space gives surprisingly good results and reduce tokens by 20 to 40% (depends on the language, python for instance)
Comment · 6 months ago
I've been building an AI coding agent that using the exact same prompt than claude code, but uses a virtual filesystem to minify source code + the concept of stem agents (general agents that specializes during the conversation for maximum cache hit). The results on my modest benchmark is 50% of claude code cost and 40% of the time.
https://github.com/kirby88/vix-releases
Comment · 7 months ago
I wonder how that compare to harness methods like MAKER https://www.cognizant.com/us/en/ai-lab/blog/maker
Comment · 5 years ago
I don't think so, you just forgot to add the remote server address. If you run `system "git", "ls-remote", " --upload-pack=$(touch hello) [email protected]:torvalds/linux.git", "HEAD"` it will fetch the remote server but still create the file on the local machine.
Comment · 5 years ago
You explained what this option is, I was asking why.
Comment · 5 years ago
I had the same reaction as you... it looks like the vulnerability is coming from git, that's a very dangerous behavior.
Comment · 5 years ago
I still don't get why the --upload-pack option execute its content... Seems pretty dangerous to me. How did you find that out?