Xander123

Ap­ply to HAIST/​MAIA’s AI Gover­nance Work­shop in DC (Feb 17-20)

AGISF adap­ta­tion for in-per­son groups

• Xander123 6 Dec 2022 7:34 UTC

  1 point

  0 ∶ 0

  in reply to: Zoe Williams’s comment on: Up­date on Har­vard AI Safety Team and MIT AI Alignment

  Thanks for this! Want to note that this was co-authored by 7 other people (the names weren’t transferred when it was crossposted from LW).

Up­date on Har­vard AI Safety Team and MIT AI Alignment

An­nounc­ing the Cam­bridge Bos­ton Align­ment Ini­ti­a­tive [Hiring!]

Ap­ply to the Red­wood Re­search Mechanis­tic In­ter­pretabil­ity Ex­per­i­ment (REMIX), a re­search pro­gram in Berkeley

• Xander123 22 Jul 2022 10:44 UTC

  19 points

  0 ∶ 0

  in reply to: hb574’s comment on: Without spe­cific coun­ter­mea­sures, the eas­iest path to trans­for­ma­tive AI likely leads to AI takeover

  I’m pretty unconvinced that your “suggests a significant number of fundamental breakthroughs remain to achieve PASTA” is strong enough to justify the odds being “approximately 0,” especially when the evidence is mostly just expecting tasks to stay hard as we scale (something which seems hard to predict, and easy to get wrong). Though it does seem that innovation in certain domains may lead to long episode lengths and inaccurate human evaluation, it also seems like innovation in certain fields (e.g., math) could easily not have this problem (i.e., in cases where verifying is much easier than solving).

An­nounc­ing the Har­vard AI Safety Team

• Xander123 8 Apr 2022 2:02 UTC

  2 points

  0 ∶ 0

  in reply to: Harrison Durland’s comment on: ‘Hot takes’ from EAGx Boston

  Worth noting that (1) the AST is for people already planning to go into alignment after graduating (and isn’t an intro program), and (2) I usually have backups prepared in case people have already read the thing (I don’t think showing up 30 minutes in would be great!).

• Xander123 7 Apr 2022 15:09 UTC

  8 points

  0 ∶ 0

  on: ‘Hot takes’ from EAGx Boston

  Thanks for the Harvard AI Safety Team shout-out! I do think in person reading is great, because it (1) creates a super low barrier to showing up, and (2) feels good/​productive to be in a room with everyone silently reading. Two points on this:

  1. We usually read for much more than 30 minutes. Our meetings are 2 hours (5:30-7:30), and often over half is silently reading (usually alternating with discussion/​lecture).

  2. Many people (myself included) prefer reading physical paper (shame!). I usually print out the readings (and I’ve given out binders). I think there are some people who learn better reading on paper, but wouldn’t be bothered to actually print things out.