Paul Christiano: "I think that Ought is one of the most promising projects working on AI alignment." Their focus: figuring out when and how evaluators can divide complex tasks into evaluable, delegatable pieces.https://www.alignmentforum.org/posts/cpewqG3MjnKJpCr7E/ought-why-it-matters-and-ways-to-help …
0 replies
8 retweets
15 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.