Is RL + LLMs enough for AGI? — Sholto Douglas & Trenton Bricken
Full Transcript
EnglishOkay. I'm joined again by my friends, Sholto Bricken... Wait
Did I do this last time? You did the same thing. No, no, you named us differently, but we didn't have Sholto Bricken and Trenton Douglas.
You swapped us. Sholto Douglas and Trenton Bricken,
who are now both at Anthropic. Yeah. Let's go. Sholto is scaling RL, Trenton's still working on mechanistic interpretability.
Welcome back. Happy to be here. Yeah, it's fun. What's changed since last year? We talked basically this month in 2024.
Unlock Full Transcript
You're viewing the first 5 lines
Register for free to access the complete transcript with timestamps
Free forever
No credit card
Showing first 5 lines • 1173 more lines available
Loading comment intelligence...
More from Dwarkesh Patel
1:35:39
Ilya Sutskever – We're moving from the age of scaling to the age of research
513,778 views
1:28:17
Satya Nadella – How Microsoft thinks about AGI
202,808 views
1:30:59
Sarah Paine — How Russia sabotaged China's rise
327,645 views
2:25:42
Andrej Karpathy — “We’re summoning ghosts, not building animals”
288,637 views
1:20:28
“I find it almost disturbing that the universe favors life this strongly” – Nick Lane
66,977 views
11:39
Some thoughts on the Sutton interview
71,527 views