News for hackers. Stuff that matters.
Re:Compare how GPT-2, 3, 3.5 and 4 answer the same questions by jellyberg on Tuesday October 31, 2023 @05:47PM (#38091865)
Yeah - worth noting that we use temperature=0 for reproducibility while ChatGPT I think uses t=0.7. We also prefix the prompt with few-shot examples of questions and answers with chain of thought examples to elicit the models' full capabilities.
Re:Compare how GPT-2, 3, 3.5 and 4 answer the same questions by DrawTR on Tuesday October 31, 2023 @09:26PM (#38093550)
Ah, gotcha! I didn't know that the few-shot thing was applicable to the newer models, that's very interesting