News for hackers. Stuff that matters.
Re:Anthropic: "Applicants should not use AI assistants" by jack_pp on Monday February 03, 2025 @06:50AM (#42917271)
The problem is he wasn't comfortable with my solution even though it was clearly faster and it could be tested instantly. It's a mental block for him and a lot of people in this industry.

I don't advocate blindly trusting LLMs. I don't either and of course test whatever it spits out.

Re:Anthropic: "Applicants should not use AI assistants" by layer8 on Monday February 03, 2025 @07:40AM (#42917595)
Testing usually isn’t enough if you don’t understand the solution in the first place. Testing is a sanity check for a solution that you do understand. Testing can’t prove correctness, it can only rind (some) errors.

LLMs are fine for inspiration in developing a solution.