HackerTrans
TopNewTrendsCommentsPastAskShowJobs

gronky_

no profile record

Submissions

Don't trust AI agents

nanoclaw.dev
344 points·by gronky_·4 maanden geleden·196 comments

Early science acceleration experiments with GPT-5 [pdf]

cdn.openai.com
5 points·by gronky_·8 maanden geleden·1 comments

comments

gronky_
·3 maanden geleden·discuss
Mobile rendering of the post has some issues. Tables are overflowing and not responsive for example
gronky_
·4 maanden geleden·discuss
Don’t know about other claws, with NanoClaw the agent can only rewrite code that runs inside the container.

You can see here that it’s only given write access to specific directories: https://github.com/qwibitai/nanoclaw/blob/8f91d3be576b830081...
gronky_
·5 maanden geleden·discuss
True. There’s a setting for Claude code though where you can add apiKeyHelper which is a script you add that gets the token for Claude Code. I imagine you can use that but haven’t quite figured out how to wire it up
gronky_
·vorig jaar·discuss
I see it a bit differently - LLMs are an incredible innovation but it’s hard to do anything useful with them without the right wrapper.

A good wrapper has deep domain knowledge baked into it, combined with automation and expert use of the LLM.

It maybe isn’t super innovative but it’s a bit of an art form and unlocks the utility of the underlying LLM