forecast
Expanding RL task horizons creates broad misalignment scope
As labs expand RL from unit tests to long-horizon goals like 'make money on the internet', such broad goals with clear objective functions are good RL tasks at high capability but carry incredible scope for misalignment.
forecastpending
Speaker
Sholto DouglasEvidence Quote
“It's actually in some ways a good RL task once you're at that level of capability, but it's also one that has incredible scope for misalignment, let's say.”
Created: 6/13/2026, 3:28:51 AM
Your notes
Loading notes...