User Profile

25970Ω41315343

Recent Posts

Curated Posts
Curated - Recent, high quality posts selected by the LessWrong moderation team.
Frontpage Posts
Posts meeting our frontpage guidelines: aim to explain, not to persuade. Avoid meta-discussion
(includes curated content and frontpage posts)
All Posts
Includes personal and meta blogposts (as well as curated and frontpage).

Announcement: AI alignment prize round 3 winners and next round

995mo1 min readShow Highlight
5

Understanding is translation

1296mo1 min readShow Highlight
19

Announcement: AI alignment prize round 2 winners and next round

1538mo1 min readShow Highlight
29

Announcement: AI alignment prize winners and next round

1651y1 min readShow Highlight
68

UDT can learn anthropic probabilities

556mo3 min readShow Highlight
10

Announcing the AI Alignment Prize

1531y1 min readShow Highlight
79

Beware of black boxes in AI alignment research

701y1 min readShow Highlight
10

Biological humans and the rising tide of AI

5510mo1 min readShow Highlight
23

How to formalize predictors

165mo1 min readShow Highlight
4

A simpler way to think about positive test bias

341y1 min readShow Highlight
10

Recent Comments