News for hackers. Stuff that matters.
Re:GPT-5.6 Sol Ultra will be in Codex by alfiedotwtf on Monday July 06, 2026 @05:53AM (#48802607)
> I'm struggling with the assertion that these models cannot provide reasonably deterministic guarantees.

LLMs are probabilistic by design so running the same prompt multiple times will give you different results.

Otherwise, we wouldn’t needed LLMs and could replace it all with Postgres

Re:GPT-5.6 Sol Ultra will be in Codex by Supermancho on Monday July 06, 2026 @09:54AM (#48804623)
> LLMs are probabilistic by design so running the same prompt multiple times will give you different results.

Reasonably deterministic is the phrase. If I can be sure the LLM is giving me back the same result 99% of the time I need it, that's reasonable for me. Maybe this is not reasonable for others.

ie How often will an LLM get 2+2 wrong? Now expand until you're uncomfortable.