Hacker News Reader

Is there any specific reason for using LLAMA embedding models instead of the new models OpenAI just released? Are they better?

Not an expert but I'd say prolly llama is preferred for privacy + open source reasons.

Not sure how much privacy is needed for a menu in a restaurant. Plus, it's all later sent to GPT which breaks privacy anyway.

There's no reason for any of this bullshit. Like cryptocurrency in 2021 this is all a solution in search of a problem.

With this particular solution, I agree.

But LLMs and RAG in general couldn't be further from crypto in terms of utility.