Comment by duskdozer

20 hours ago

The difference is that LLM output is very nondeterministic.

And because of that, we check in the generated code, not the high-level abstraction. So to understand your program, you have to read the output, not the input.

It depends. Temperature is a variable. If you really need determinism, you could build a LLM for that. Non-determinism can be a good feature though.

  • How would you do that? If it's possible, it seems strange that someone hasn't done it already.

    • Totally possible and we can already do it ! Simply put, just set the temperature to 0 and reuse the same seed. But it's just not what people really want, and providers are reluctant because they cost up to 5x more to generate. It's also not 100% non-deterministic, because cloud providers don't run on the same hardware, with the same conditions required for producing the same output. So, in practice, not so good, but in theory if you need it and can afford it, you can.