minus-squarejoelthelion@lemmy.worldtoTechnology@lemmy.world•Tech experts are starting to doubt that ChatGPT and A.I. ‘hallucinations’ will ever go away: ‘This isn’t fixable’linkfedilinkEnglisharrow-up0·1 year agoI don’t understand why they don’t use a second model to detect falsehoods instead of trying to fix it in the original LLM? linkfedilink
I don’t understand why they don’t use a second model to detect falsehoods instead of trying to fix it in the original LLM?