News for hackers. Stuff that matters.

A comment on From GPT-4 to GPT-5: Measuring Progress in Medical Language Understanding [pdf]. Parent comment

Re:From GPT-4 to GPT-5: Measuring Progress in Medical Langua... by platypii on Friday August 22, 2025 @12:08AM (#44980906)
Why not? We are trying to evaluate AI's capabilities. It's OBVIOUS that we should compare it to our only prior example of intelligence -- humans. Saying we shouldn't compare or anthropomorphize machine is a ridiculous hill to die on.
[ Parent | on HN ]
Re:From GPT-4 to GPT-5: Measuring Progress in Medical Langua... by sema4hacker on Saturday August 23, 2025 @12:09AM (#44993069)
If you are comparing the performance of a computer program with the performance of a human, then using terms implying they both "understand" wrongly implies they work in the same human-like way, and that ends up misleading lots of people, especially those who have no idea (understanding!) how these models work. Great for marketing, though.
[ Parent | on HN ]