51–60 of 126 posts
Earlier quoted context omitted.
I think it probably works a lot better, but I would love to see some research validating this
I've read in a few places that it actually works worse in most cases. Much better to put the context in your prompt.
Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
When is fine tuning worth it, rather than just prompt engineering?
Earlier quoted context omitted.
I don't think that works. LLM-generated contents are not copyrightable.
Breach of contract for violating the TOS agreed to when signinf uo for the service doesn’t depend on copyright.
Earlier quoted context omitted.
Breach of contract for violating the TOS agreed to when signinf uo for the service doesn’t depend on copyright.
Right but cease and desist usually relates to intellectual property or copyright matters, typically not TOS violations. Please correct me if I am mistaken.
Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
> I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? Yes, almost all improved LLama models are tuned exactly that way (trained on examples of questions and answers from say GPT 4). If OpenAI stole copyrighted works to train their models it is morally fair game to do the same to them regardless of their TOS. It's not like they can prove it anyway. Plus there's the other po…
I don't mind just making a point.
But I don't think they mind. I don't believe that this type of model training is able to be bleeding edge which should guarantee that openai has enough motivation to continue the development and having a healthy competition
Earlier quoted context omitted.
I've read in a few places that it actually works worse in most cases. Much better to put the context in your prompt.
Fine tuning + context will outperform context alone, and it's cheaper to burn cycles fine tuning then use a smaller context than to use a larger context in production.
Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"
> I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? Yes, almost all improved LLama models are tuned exactly that way (trained on examples of questions and answers from say GPT 4). If OpenAI stole copyrighted works to train their models it is morally fair game to do the same to them regardless of their TOS. It's not like they can prove it anyway. Plus there's the other po…
Can someone explain why I'd want to use fine-tuning instead of a vector database (or some other way of storing data/context)?
Wouldn't a vector database just get you nearest-neighbors on the embeddings? How would that answer a generative or extractive question? I can see it might get you sentiment, but would it help with "tell me all the places that are mentioned in this review"?
Earlier quoted context omitted.
I don't think that works. LLM-generated contents are not copyrightable.
Breach of contract for violating the TOS agreed to when signinf uo for the service doesn’t depend on copyright.
Once Alice has done that, is there anything to prevent Bob, who has never agreed to ChatGPT ToS, to use those prompts and outputs to train his own models to compete with OpenAI's?
(Purely from a contractual/legal/IP angle rather than ML/technical.)