Comment on How Much Do LLMs Hallucinate in Document Q&A Scenarios? A 172-Billion-Token Study Across Temperatures, Context Lengths, and Hardware Platforms [TLDR: 25%]

<- View Parent
dogzilla@masto.deluma.biz ⁨2⁩ ⁨weeks⁩ ago

@eceforge @technology I never understood why we don’t just call it “lying”. I mean, I understand why AI companies don’t call it that, but that’s what it is and I don’t think we’re helping ourselves by using a euphemism

source
Sort:hotnewtop