What might an empirical investigation of alignment look like? Can you illustrate with an example?
Both Redwood and Anthropic have labs and do empirical work. This is also an example of experimental work: https://twitter.com/Karolis_Ram/status/1540301041769529346
What might an empirical investigation of alignment look like? Can you illustrate with an example?
Both Redwood and Anthropic have labs and do empirical work. This is also an example of experimental work: https://twitter.com/Karolis_Ram/status/1540301041769529346