News for hackers. Stuff that matters.

A comment on LLMs can't perform "genuine logical reasoning," Apple researchers suggest. Parent comment

Re:LLMs can't perform "genuine logical reasoning," Apple res... by boroboro4 on Tuesday October 15, 2024 @11:56AM (#41849891)
And that's why OpenAI o1 will use chain of thoughts for this particular question rather than hallucinate approximate answer. And it does work just like before by generating token by token.
[ Parent | on HN ]
Re:LLMs can't perform "genuine logical reasoning," Apple res... by janalsncm on Tuesday October 15, 2024 @07:01PM (#41853999)
Here are some actual performance metrics:

https://x.com/yuntiandeng/status/1836114401213989366

If chain of thought really worked we should see no difference between 1 digit and 20 digit multiplication.

[ Parent | on HN ]