RSS

Ryan Greenblatt

Karma: 1,605

This other Ryan Greenblatt is my old account[1]. Here is my LW account.

  1. ^

    Account lost to the mists of time and expired university email addresses.

Dist­in­guish be­tween in­fer­ence scal­ing and “larger tasks use more com­pute”

Ryan Greenblatt11 Feb 2026 18:37 UTC
29 points
3 comments2 min readEA link

When is it im­por­tant that open-weight mod­els aren’t re­leased? My thoughts on the benefits and dan­gers of open-weight mod­els in re­sponse to de­vel­op­ments in CBRN ca­pa­bil­ities.

Ryan Greenblatt9 Jun 2025 19:19 UTC
39 points
3 comments9 min readEA link

AI com­pa­nies are un­likely to make high-as­surance safety cases if timelines are short

Ryan Greenblatt23 Jan 2025 18:41 UTC
45 points
1 comment13 min readEA link

Align­ment Fak­ing in Large Lan­guage Models

Ryan Greenblatt18 Dec 2024 17:19 UTC
143 points
9 comments10 min readEA link

Thoughts on SB-1047

Ryan Greenblatt30 May 2024 0:19 UTC
53 points
4 comments11 min readEA link

Ryan Green­blatt’s Quick takes

Ryan Greenblatt3 Feb 2024 17:55 UTC
3 points
14 commentsEA link

Im­prov­ing the Welfare of AIs: A Nearcasted Proposal

Ryan Greenblatt30 Oct 2023 14:57 UTC
57 points
0 comments20 min readEA link
(www.lesswrong.com)