News for hackers. Stuff that matters.

A comment on Command A: Max performance, minimal compute – 256k context window. Parent comment

Re:Command A: Max performance, minimal compute – 256k contex... by vmg12 on Sunday March 16, 2025 @10:51AM (#43379497)
Here is an even easier one, ask llms to take the integral from 0 to 3 of 1/(x-1)^3. It fails to notice it's an improper integral and just gives an answer.
[ Parent | on HN ]
Re:Command A: Max performance, minimal compute – 256k contex... by floam on Sunday March 16, 2025 @03:18PM (#43381397)
ChatGPT definitely noticed: o1, o3-mini, o3-mini-high.

Maybe 4o will get it wrong? I wouldn’t try it for math.

[ Parent | on HN ]
Re:Command A: Max performance, minimal compute – 256k contex... by vmg12 on Sunday March 16, 2025 @11:45PM (#43385002)
I tried 4.5 which i thought was the best model, seems like the reasoning models do get it.
[ Parent | on HN ]