Hot Issue 40일 전
Models Are Getting Dumber on Purpose
소스 기사
[4 건] HN
Hacker News • 40일 전
IMP 5
Models Are Getting Dumber on Purpose
TD
The Decoder • 40일 전
IMP 5
When AI models aren't allowed to reflect on themselves, it changes their entire worldview
TD
The Decoder • 41일 전
IMP 5
Optima tackles AI benchmarking's biggest flaw by letting users test models against their own data
TD
The Decoder • 42일 전
IMP 3
New benchmark confirms AI models still perform poorly at visual perception
[요약 오류] New benchmark confirms AI models still perform poorly at visual perception