Flutterby™! : Legal RAG

Stanford University Human Centered Artificial Intelligence: AI on Trial: Legal Models Hallucinate in 1 out of 6 (or More) Benchmarking Queries

In a new preprint study by Stanford RegLab and HAI researchers, we put the claims of two providers, LexisNexis (creator of Lexis+ AI) and Thomson Reuters (creator of Westlaw AI-Assisted Research and Ask Practical Law AI)), to the test. We show that their tools do reduce errors compared to general-purpose AI models like GPT-4. That is a substantial improvement and we document instances where these tools provide sound and detailed legal research. But even these bespoke legal AI tools still hallucinate an alarming amount of the time: the Lexis+ AI and Ask Practical Law AI systems produced incorrect information more than 17% of the time, while Westlaw’s AI-Assisted Research hallucinated more than 34% of the time.

So, yeah, "Retrieval Augmented Generation" is "here's your search results, but with an additional layer of bullshit generation".

In linking to it, Peter Krupa notes

GenAI is this poison pill that every monopoly business is frantically swallowing because of FOMO, it’s crazy, honestly almost like this whole thing was planned by the “Fight Club” weirdos to bring everything down at once.