Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

"Manage people using RL, not SFT" Set goals, reward, but avoid reward hacking. Kimi's CEO, Zhilin Yang's thoughts on company management. Interesting to hear management skills from a machine learning mindset. It's really similar to Hyung Won Chung's thought "don't teach, incentivize" > which i've set as working bio...

87,808 görüntüleme • 10 ay önce •via X (Twitter)

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar