Hacker News Reader

Hmm, is faster hallucination better than slower hallucination?

When the answers can be checked by another program and best-of-n results get better with increasing n, yes.

I think TDD code development is this, at least in principle.

If you can write a program to check results you've already solved the issue.

Sometimes.

Some things are easier to verify than to generate.

LLMs can often make a distribution of generated outputs that is much closer to a good answer than other methods.

Maybe if you hallucinate fast enough no one will notice?

I was initially reading it as LLVM performance and thought, “how cool” and then I realized the V was missing and stopped caring.