RSS

Michaël Trazzi

Karma: 365 (LW), 6 (AF)
Page 1

A Gym Grid­world En­vi­ron­ment for the Treach­er­ous Turn

Michaël Trazzi
28 Jul 2018 21:27 UTC
66 points
9 comments3 min readLW link
(github.com)

Book Re­view: AI Safety and Security

Michaël Trazzi
21 Aug 2018 10:23 UTC
54 points
2 comments11 min readLW link

Hu­man-Aligned AI Sum­mer School: A Summary

Michaël Trazzi
11 Aug 2018 8:11 UTC
44 points
5 comments4 min readLW link

Sto­ries of Con­tin­u­ous Deception

Michaël Trazzi
31 May 2019 14:31 UTC
19 points
5 comments2 min readLW link

Treach­er­ous Turn, Si­mu­la­tions and Brain-Com­puter Interfaces

Michaël Trazzi
25 Feb 2019 15:49 UTC
17 points
0 comments5 min readLW link

The Mul­ti­ple Names of Benefi­cial AI

Michaël Trazzi
11 May 2018 11:49 UTC
17 points
0 comments3 min readLW link

Should an AGI build a telescope to spot in­ter­galac­tic Seg­ways?

Michaël Trazzi
28 Apr 2018 21:55 UTC
14 points
6 comments2 min readLW link

Open Thread Oc­to­ber 2018

Michaël Trazzi
2 Oct 2018 18:01 UTC
13 points
21 comments1 min readLW link

A Lo­gi­cian, an En­trepreneur, and a Hacker, dis­cussing Intelligence

Michaël Trazzi
1 May 2018 20:45 UTC
11 points
0 comments2 min readLW link

A Treach­er­ous Turn Timeline—Chil­dren, Seed AIs and Pre­dict­ing AI

Michaël Trazzi
21 May 2019 19:58 UTC
9 points
6 comments3 min readLW link

Beliefs: A Struc­tural Change

Michaël Trazzi
6 May 2018 13:40 UTC
9 points
7 comments2 min readLW link

Con­sid­er­ate­ness in OpenAI LP Debate

Michaël Trazzi
12 Mar 2019 19:05 UTC
8 points
1 comment1 min readLW link
(medium.com)

[Question] Great­est Lower Bound for AGI

Michaël Trazzi
5 Feb 2019 20:17 UTC
8 points
17 comments1 min readLW link

Build­ing Safer AGI by in­tro­duc­ing Ar­tifi­cial Stupidity

Michaël Trazzi
14 Aug 2018 15:54 UTC
8 points
7 comments1 min readLW link
(arxiv.org)

Talk­ing about AI Safety with Hikers

Michaël Trazzi
10 May 2018 6:38 UTC
8 points
0 comments4 min readLW link