AI ALIGNMENT FORUMTags
AF

Ought

•

Applied to Ought will host a factored cognition “Lab Meeting” by jungofthewon 1y ago

•

Applied to Rant on Problem Factorization for Alignment by Multicore 1y ago

•

Applied to Prize for Alignment Research Tasks by Andreas Stuhlmüller 1y ago

•

Applied to Elicit: Language Models as Research Assistants by Andreas Stuhlmüller 1y ago

•

Applied to Supervise Process, not Outcomes by Andreas Stuhlmüller 1y ago

•

Applied to Forecasting Thread: Existential Risk by MichaelA 2y ago

•

Applied to GPT-3 and the future of knowledge work by plex 3y ago

•

Applied to Beta test GPT-3 based research assistant by Multicore 3y ago

•

Applied to Automating reasoning about the future at Ought by Ben Pace 3y ago

•

Applied to The Majority Is Always Wrong by Raymond Arnold 3y ago

•

Applied to Current AI Safety Roles for Software Engineers by Multicore 3y ago

•

Applied to Factored Cognition by Ben Pace 3y ago

•

Applied to Solving Math Problems by Relay by Ben Pace 3y ago

•

Applied to The Stack Overflow of Factored Cognition by Ben Pace 3y ago

•

Applied to [AN #86]: Improving debate and factored cognition through human experiments by Ben Pace 3y ago

•

Applied to Update on Ought's experiments on factored evaluation of arguments by Ben Pace 3y ago

•

Applied to Ought: why it matters and ways to help by Ben Pace 3y ago

Ben Pace v1.0.0Jul 22nd 2020 (+90)

Ought is an AI alignment research non-profit focused on the problem of Factored Cognition.

•

Created by Ben Pace at 3y