Comment by superkuh

I've spent an embarassing amount of time since the llamas leaked playing with them, the tools to run them, and writing wrappers for them. They are technically alternatives in the sense that they're incomparably better chat bots than anything in the past. But at least for the 30B and under versions (65B is too big for me to run), no matter what fine tuning is done (alpaca, gpt4all, vicuna, etc), the llamas themselves are incomparably worse at doing useful tasks than openai's gpt3.5 models like text-davinci-003, or even the gimped gpt3.5-turbo.

I wish it wasn't so, but the llamas are toys. Amazing toys, but toys. What openai is getting out of gpt3.5 (and presumbably 4, though I have no access) are actually useful responses for getting work done.