No the whole
Point is you make a gpt for yourself and upload all your related documents to it and then query that. It performs 10x better than a generic query without attaching every single doc that could be relevant.
I am unsure if the answer is to use “projects” maybe this has superseded myGpts?
I am perplexed why HN isn’t focusing on this issue as all the Llm gains I’ve ever had were wit highly customised personal myGpts.
I can understand OpenAI and Sam’s having access to their own models may not even know what the best way to use the released stuff is
This is something being done but not for consumers right now. On a more roll your own basis. I know a few people whose companies have already established their own gpt trained on their own internal codebase, standards, documentation, and I’m sure relevant reference information as well. Think big r and d companies in stem.
I am unsure if the answer is to use “projects” maybe this has superseded myGpts?
I am perplexed why HN isn’t focusing on this issue as all the Llm gains I’ve ever had were wit highly customised personal myGpts.
I can understand OpenAI and Sam’s having access to their own models may not even know what the best way to use the released stuff is
Ps - typing on my phone hence typos