[famouswaffles]

Bigger models hallucinate less.

and we don't call it hallucinations but gofai mispredicts plenty.

[xpe]

> Bigger models hallucinate less.

I'm skeptical. Based on what research?

[famouswaffles]

GPT-4 hallucinates a lot less than 3.5. Same with the Claude Models. This is from personal experience. There are also benchmarks (like TruthfulQA) that try to measure hallucinations that show the same thing.