01 / evaluation
Afterwards, when pushes into big reinforcement learning efforts kind of all fizzled out—like post-Dota, as the reinforcement learning wasn't working out for solving those hard problems outside of the simulated game universes—then I started thinking, “Okay, maybe we kinda overshot there…” But then GPT came out of nowhere and basically erased all that.
“Afterwards, when pushes into big reinforcement learning efforts kind of all fizzled out—like post-Dota, as the reinforcement learning wasn't working out for solving those hard problems outside of the simulated game universes—then I started thinking, “Okay, maybe we kinda overshot there…” But then GPT came out of nowhere and basically erased all that.”
- Speaker
- Gwern
- Publisher
- Dwarkesh Podcast