News for hackers. Stuff that matters.
Re:OpenAssistant Conversations – Democratizing Large Languag... by KolmogorovComp on Saturday April 15, 2023 @05:43PM (#35584846)
Side question, but how do these models are benchmarked, and how is this subfield evolving these days? I have seen many papers relying on standard student tests performance, but they don’t seem very accurate since LLAMA-based models perform almost as good as chatGPT (3/3.5) despite being apparently being an order of magnitude worse in practice.

There are no comments on this comment yet.