I'm rather surprised to hear this. This feels like a post from about 18 months ago. I can't remember the last time I encountered a genuine code hallucination from a frontier model. They have other issues, but rarely this.

What kind of domain are you working in?

I see subtle ones at least daily, misunderstanding a component or hallucination of a spec for something. I’m in blockchain.

C++ and Unreal Engine but it has full source access. If you're actually trying to deep dive on bugs, it's still confidently wrong a lot of the time.

It's a bit better than 18 months ago but it's hard to say by how much. It just seems like the culture has moved to building up fixtures that let the LLMs brute force the problems. To my eyes that's the opposite of solving things logically. It has the added effect of hiding how the sausage is made, though.

I mean, how can they possibly say they haven't written a line of code if they're actually going through it? I can only assume they're just looking at the results. So then how can they judge it's good at logic?

If it was so good at not making mistakes, why even have tests? It's nonsensical on its face.