News for hackers. Stuff that matters.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by mbesto on Friday May 16, 2025 @09:53AM (#44005551)
> That's because models have training cut-off dates.

Which is precisely the issue with the idea of LLMs completely replacing human engineers. It doesn't understand this context unless a human tells it to understand that context.

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by simonw on Saturday May 17, 2025 @09:08PM (#44018209)
Right: the idea that LLMs are a replacement for human engineers is deeply flawed in my opinion.