Re:Telling GPT-4 you're scared or under pressure improves pe...
by og_kalu on Sunday November 05, 2023 @11:04PM
(#38158711)
>If you ask llm to solve a math problem it haven't seen its response will be closer to the desired solution in its linguistic form rather than in mathematical meaning.
This isn't true. Wild how people will confidently say nonsense about things they obviously haven't actually tested.
GPT-4 can manage arbitrary arithmetic calculation closer to the real value than you could ever do without an external tool.
Re:Telling GPT-4 you're scared or under pressure improves pe...
by scotty79 on Saturday November 11, 2023 @03:59AM
(#38228635)
I don't mean calculations. I mean math problems.
Like those: https://www.mathschool.com/locations/andover/news/prepare-fo...
Re:Telling GPT-4 you're scared or under pressure improves pe...
by fragmede on Saturday November 11, 2023 @05:19AM
(#38228999)
ChatGPT-4 is quite capable of solving problems like that.
Here's it solving the last two problems on the Grade 7-8 Russian Math Olympiad from the linked page.
https://chat.openai.com/share/e90d4711-aa38-45c5-97e7-a9a04e...
https://chat.openai.com/share/0c9c579a-ca9f-4aa6-bac6-624372...
The two answers (84 and 225,792) agree with the answer key. I only gave it the questions and didn't give it the PDF either, so it didn't cheat and just read the answer off the answer key in the PDFs.
Yes. We can infer from this that out of sample hallucinations will be closer to the desired productions when measured by token productions metrics than by any other more informative domain relevant metrics.
Which is exactly the case.
If you ask llm to solve a math problem it haven't seen its response will be closer to the desired solution in its linguistic form rather than in mathematical meaning.