alt Hacker NewsI don’t think that the logical reasoning ability of LLMs depends on the abstraction level. Their heuristic knowledge differs between levels, but that’s a different thing. My concern is the reasoning capabilities.
I don’t think that the logical reasoning ability of LLMs depends on the abstraction level. Their heuristic knowledge differs between levels, but that’s a different thing. My concern is the reasoning capabilities.
And so you experience that AI generated code, even on lower levels, is not good enough for you to be more productive?