This is a special post for quick takes by J Bostock. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
I'll be visiting Berkeley for the first time from the 14th to the 20th of April. I'm hoping to talk to people working seriously in technical AI alignment (as well as just generally meeting the Berkeley rats). I'm going to be starting a new position in May, where I expect to have a decent amount of influence over the research direction of the team, and I'd like to get as good of an idea as possible of the strategic landscape of technical safety.
(honestly unsure how much I can say, although the position was publicly advertised)
It's an org in London which didn't previously have a full-time research team but recently got a grant from AISI to hire a team full-time for (at least) a year, and will be collaborating with AISI on some of the research.