Talk:GPT-4/Archive 2
This is an archive of past discussions about GPT-4. Do not edit the contents of this page. If you wish to start a new discussion or revive an old one, please do so on the current talk page. |
Archive 1 | Archive 2 |
Wiki Education assignment: Research Process and Methodology - SP24 - Sect 201 - Thu
This article was the subject of a Wiki Education Foundation-supported course assignment, between 4 March 2024 and 4 May 2024. Further details are available on the course page. Student editor(s): Jrxijown (article contribs).
— Assignment last updated by Jrxijown (talk) 00:05, 31 March 2024 (UTC)
What is the vocabulary size of GPT?
Open AI has released the tokenizer for all of its models, we should have access to this info Ilya.gazman (talk) 03:43, 10 April 2024 (UTC)
160.119.47.79 (talk) 15:14, 29 April 2024 (UTC)
JAMA pediatric study
This study used GPT 3.5, not 4. The study (technical it was a research letter, not a peer-reviewed article) was widely discredited because the prompt was simply, "List a differential diagnosis and a final diagnosis" and the case information. Given that no attempt at prompt engineering was made and the old GPT model was used (6 months after the release of GPT4), it appears more like a smear attempt. 170.85.70.173 (talk) 16:06, 13 June 2024 (UTC)