| ▲ | orbital-decay 3 hours ago | ||||||||||||||||
Yeah but what stops it from producing confidently incorrect outputs... | |||||||||||||||||
| ▲ | zenlikethat 2 hours ago | parent [-] | ||||||||||||||||
Nothing, but imagine using LLMs for a classification task People out there are so resigned to the models being unreliable that they are really doing things like hallucinating deliberately, and then matching the hallucinations to embeddings - https://softwaredoug.com/blog/2026/08/10/hypothetical-classi... You could do that or you could just... use a model that will never produce unreliable outputs in the first place. | |||||||||||||||||
| |||||||||||||||||