Re:What we learned from using GPT for 500k+ classifications
by PartiallyTyped on Wednesday July 12, 2023 @02:21PM
(#36699316)
I can’t provide an example as I would rather not jeopardise my employment and livelihood.
The domain is actually novel, is not a subdomain in any way whatsoever unless you consider “next token prediction” to be the class of all possible problems that LLMs may be used for.
As for the parameter change remark, prompts change the __effective__ parameters of the model. [0]
The domain is actually novel, is not a subdomain in any way whatsoever unless you consider “next token prediction” to be the class of all possible problems that LLMs may be used for.
As for the parameter change remark, prompts change the __effective__ parameters of the model. [0]
[0] https://arxiv.org/abs/2212.10559