This is really great, thank you! It feels like it’s a one-stop-shop for a lot of the most important ideas and arguments that have been developed on the topic of deep learning misalignment over the past few years.
Possibly relevant empirical evidence has arrived!
Also this one here of CoT samples!
This is really great, thank you! It feels like it’s a one-stop-shop for a lot of the most important ideas and arguments that have been developed on the topic of deep learning misalignment over the past few years.
Possibly relevant empirical evidence has arrived!
Also this one here of CoT samples!