Can we solve difficult problems by composing small contributions from individual agents who don't know the big picture?| ought.org
This is an update on the work on AI Safety via Debate that we previously wrote about here. …| www.alignmentforum.org
A high-level view on the elusive once-and-for-all solution| aligned.substack.com
An explanation using the language of machine learning| aligned.substack.com
Bootstrapping a solution to the alignment problem| aligned.substack.com
How to scale alignment techniques to hard tasks| aligned.substack.com