OpenAI Lifeboat – Proxy OpenAI Code to Llama 70B on Replicate

by Charlieholtz on 11/22/2023, 12:35:07 AM with 3 comments

  • by xeckr on 11/22/2023, 1:22:08 AM

    I understand that LLaMa 70B isn't even at GPT-3's level yet.

    If you have paying customers who expect GPT-4-level quality, is using LLaMa 70B to generate responses really better than just telling users that the OpenAI API is temporarily down, from a reputational standpoint?

  • by upwardbound on 11/22/2023, 1:12:41 AM

    Clever. That’s pretty neat that they were able to make their API perfectly drop-in compatible.