1. W We still have time to change to rules of the scaling race, but maybe not a lot. AI will keep improv... We still have time to change to rules of the scaling race, but maybe not a lot. AI will keep improving rapidly and the stakes will increase. Unless we have pacing mechanisms that a 09/11 01:31 ♡
2. T The upsides of AI will be massive, but it'll still take many years for them to bear fruit. Let's be ... The upsides of AI will be massive, but it'll still take many years for them to bear fruit. Let's be a bit more patient with them, so we can reduce the risks associated with 09/11 01:31 ♡
3. N Now is a good time to build institutional mechanisms to pace the frontier of AI development. The in... Now is a good time to build institutional mechanisms to pace the frontier of AI development. The industry is locked into an all-out scaling race to build superintelligence as quick 09/11 01:31 ♡
4. I I'm so grateful to all the insanely talented people I got to work with on alignment over the years. ... I'm so grateful to all the insanely talented people I got to work with on alignment over the years. It's a real privilege to work with people so deeply motivated to make th 05/09 01:48 ♡
5. S Some personal news: I am starting a new research project at Anthropic. Very excited about this! Man... Some personal news: I am starting a new research project at Anthropic. Very excited about this! Many things are needed to make AGI go well, and alignment is only one of them. More 05/09 01:48 ♡
6. W When I started to work on the alignment problem more than 10 years ago, we had no idea how AGI was g... When I started to work on the alignment problem more than 10 years ago, we had no idea how AGI was going to be built or how to make it safe. The field had maybe a dozen people who 05/09 01:48 ♡
7. T To focus on this, I’ve stepped away from running alignment at Anthropic. @EthanJPerez and @sprice354... To focus on this, I’ve stepped away from running alignment at Anthropic. @EthanJPerez and @sprice354_ are leading the team going forward, and I’m confident they’ll do an amazing jo 05/09 01:48 ♡
8. I'm really excited about this as a new tool in our interpretability tool kit I'm really excited about this as a new tool in our interpretability tool kit Samuel Marks @saprmarks In a new paper, we present NLAs, an unsupervised method for converting an L 05/08 01:48 ♡
9. A Awesome work by @jiaxinwen22, @liangqiu_1994, Joe Benton, and @janhkirchner! For more details, chec... Awesome work by @jiaxinwen22 , @liangqiu_1994 , Joe Benton, and @janhkirchner ! For more details, check out the blog post 👇 anthropic.com/research/autom… 1 💬 9  04/15 03:43 ♡
10. H However, most alignment research is not very crisp and requires research taste when evaluating. Thi... However, most alignment research is not very crisp and requires research taste when evaluating. This is why we chose to point the AAR at this scalable oversight problem! Progress w 04/15 03:43 ♡
