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 Douglas

Evidence 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.”

Source

Is RL + LLMs enough for AGI? — Sholto Douglas & Trenton Bricken— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:51 AM

Your notes

Loading notes...