from Hacker News

Open-source reflection lama 70B beats Claude 3.5 and GPT-4 on benchmarks

by oldcai on 9/7/24, 9:09 AM with 4 comments

• by magicalhippo on 9/7/24, 10:55 AM

  Related recent discussion:

  Reflection 70B, the top open-source model

  https://news.ycombinator.com/item?id=41459781

• by morbicer on 9/7/24, 1:35 PM

  I must be missing something but the model is absolutely useless because it's giving unrelated answers.

  Check the questions people posted:

  https://reflectionllama.com/discover