absorb.md

Reward Is Enough

2 mentions across 2 people

Google DeepMind
youtube · 2026-04-07
Recommended

the last time I got to speak to you on this podcast we talked about a a different position paper that you had just written uh reward is enough essentially saying that reinforcement learning is all you need to get you towards AGI do you still think that that's the case

The Era of Experience: Moving Beyond Human Data in AI