LLMs Missing Value Functions
43:42–44:25 · 43s
Adam marvels that today's language models ignore the very idea of value functions, calling the approach “crazy” compared with classic reinforcement learning.
43:42–44:25 · 43s
Adam marvels that today's language models ignore the very idea of value functions, calling the approach “crazy” compared with classic reinforcement learning.
We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.