What is Ought's research agenda?

Ought is a research lab that "develops mechanisms for delegating high-quality reasoning to advanced machine learning systems." Its research focuses on methods for breaking up complex, hard-to-verify tasks into simpler, easier-to-verify tasks, with the aim of allowing us to maintain effective oversight over AIs.

As of June 2023, Ought aims to automate and scale open-ended reasoning through Elicit, an AI research assistant. Ought focuses on advancing process-based systems rather than outcome-based ones; they believe this to be beneficial for improving both reasoning in the short term and alignment in the long term.

Ought hopes its work will (a) improve reasoning of AI governance & alignment researchers, particularly on long-horizon tasks, and (b) push supervision of process rather than outcomes, which reduces the optimization pressure on imperfect proxy objectives leading to “safety by construction”. Ought argues that the race between process and outcome-based systems is particularly important because both states may be an attractor.