News for hackers. Stuff that matters.
Re:I will not be using LLMs in my coding by ricardobeat on Sunday November 08, 2026 @08:47AM (#50413345)
These anecdotes mean nothing without knowing context, model, harness, prompt. The technology has moved a lot in the past year.

To that end, my very first experience with OpenCode let to a `rm -rf /` within minutes, which I caught by chance watching the streaming output. Now I know what I'm doing, every agent is sandboxed, better tooling and models.

Re:I will not be using LLMs in my coding by xigoi on Sunday November 08, 2026 @10:47AM (#50414253)
Ah yes, the favorite response to any criticism of LLMs – you are using the wrong model.