You can disable this behavior globally. Yes, the agent should have no git access this way, however you could always do a local sub repository if you want to. You track your changes twice, but should work

This way you don't have to give git access to the potentially unsafe server. Git hook attacks are still possible so disable those by defaultç

This is an unusual folder structure but works fine, let me know if there is anything iffy

At that point one could argue that running your own server to get instant responses from your llm matters, while we are at it, compile times, tests, search queries, could always use be shaved some milliseconds per.

With speed reader tools I can comfortably read and understand 500 wpm, should we now switch to speed readers since we read code more often than we write it ?

No, in reality, you create software faster when the code you write the first time doesn't result in errors, which requires knowledge of your stack.

Even if you are not looking to read your code, LLMs also benefit from good programming practices, some of these programming practices should produce code which is clear, changeable and extendable

This sounds similar to the Kimi's mixture of experts architecture if I understood it correctly(likely I have not), can you comment on this ?

First play through I found the difficulty a bit much, but I think some geowizards will disagree

I like it for idea exploration

Something for adding details under a branch could be nice

Something like LLM token usage is one of those new metrics that people like to share, I can see this being a thing

It is just a simple collection of useful commands that are executed via ssh to see what the server is like for now.

I think this is useful when you inherit a server with only an ssh connection and no documentation, or when trying to troubleshoot and need context for your LLM

Comments URL: https://news.ycombinator.com/item?id=45611104

Points: 2

# Comments: 0