Karma: 309

Contact me via LessWrong or at m[dot]arc[dot]er[underscore]contact[at]proton[dot]me

The Löbian Ob­sta­cle, And Why You Should Care

marc/er7 Sep 2023 23:59 UTC
17 points
6 comments2 min readLW link

The Utility and Sol­u­bil­ity of An­thropic Capture

marc/er3 Aug 2023 5:33 UTC
11 points
1 comment7 min readLW link

[Question] What Does LessWrong/​EA Think of Hu­man In­tel­li­gence Aug­men­ta­tion as of mid-2023?

marc/er8 Jul 2023 11:42 UTC
84 points
28 comments2 min readLW link

Direct Prefer­ence Op­ti­miza­tion in One Minute

marc/er26 Jun 2023 11:52 UTC
14 points
3 comments1 min readLW link

Par­tial Si­mu­la­tion Ex­trap­o­la­tion: A Pro­posal for Build­ing Safer Simulators

marc/er17 Jun 2023 13:55 UTC
16 points
0 comments10 min readLW link

Higher Di­men­sion Carte­sian Ob­jects and Align­ing ‘Tiling Si­mu­la­tors’

marc/er11 Jun 2023 0:13 UTC
22 points
0 comments5 min readLW link