User Profile

Ω661327

Recent Posts

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

Standard ML Oracles vs Counterfactual ones

Stuart_Armstrong5d5 points5 min readShow Highlightsubdirectory_arrow_left
0

Bridging syntax and semantics with Quine's Gavagai

Stuart_Armstrong21d5 points1 min readShow Highlightsubdirectory_arrow_left
1

Wireheading as a potential problem with the new impact measure

Stuart_Armstrong20d8 points4 min readShow Highlightsubdirectory_arrow_left
19

Disagreement with Paul: alignment induction

Stuart_Armstrong1mo3 points1 min readShow Highlightsubdirectory_arrow_left
4

Web of connotations: Bleggs, Rubes, thermostats and beliefs

Stuart_Armstrong1mo3 points7 min readShow Highlightsubdirectory_arrow_left
0

Using expected utility for Good(hart)

Stuart_Armstrong2mo6 points6 min readShow Highlightsubdirectory_arrow_left
1

Petrov corrigibility

Stuart_Armstrong1mo3 points1 min readShow Highlightsubdirectory_arrow_left
9

Bridging syntax and semantics, empirically

Stuart_Armstrong1mo1 point5 min readShow Highlightsubdirectory_arrow_left
0

Boltzmann brain decision theory

Stuart_Armstrong1mo3 points6 min readShow Highlightsubdirectory_arrow_left
0

Corrigibility doesn't always have a good action to take

Stuart_Armstrong2mo4 points1 min readShow Highlightsubdirectory_arrow_left
0

Recent Comments