RSS

mishka

Karma: 1,628

Exploring non-anthropocentric aspects of AI existential safety: https://​​www.lesswrong.com/​​posts/​​WJuASYDnhZ8hs5CnD/​​exploring-non-anthropocentric-aspects-of-ai-existential (this is a relatively non-standard approach to AI existential safety, but this general direction looks promising).

Some of the ways the IABIED plan can backfire

mishka22 Sep 2025 15:02 UTC
19 points
16 comments2 min readLW link

mishka’s Shortform

mishka28 May 2024 17:38 UTC
5 points
10 comments1 min readLW link

Digi­tal hu­mans vs merge with AI? Same or differ­ent?

Nathan Helm-Burger and mishka
6 Dec 2023 4:56 UTC
21 points
11 comments7 min readLW link

[Question] What is known about in­var­i­ants in self-mod­ify­ing sys­tems?

mishka2 Dec 2023 5:04 UTC
9 points
2 comments1 min readLW link

Some In­tu­itions for the Ethicophysics

MadHatter and mishka
30 Nov 2023 6:47 UTC
2 points
4 comments8 min readLW link

[Question] Im­pres­sions from base-GPT-4?

mishka8 Nov 2023 5:43 UTC
26 points
25 comments1 min readLW link

Ilya Sutskever’s thoughts on AI safety (July 2023): a tran­script with my comments

mishka10 Aug 2023 19:07 UTC
22 points
3 comments5 min readLW link

[Question] What to read on the “in­for­mal multi-world model”?

mishka9 Jul 2023 4:48 UTC
13 points
23 comments1 min readLW link

Re­cur­ren­tGPT: a loom-type tool with a twist

mishka25 May 2023 17:09 UTC
10 points
0 comments3 min readLW link
(arxiv.org)

Five Wor­lds of AI (by Scott Aaron­son and Boaz Barak)

mishka2 May 2023 13:23 UTC
22 points
6 comments1 min readLW link1 review
(scottaaronson.blog)

Ex­plor­ing non-an­thro­pocen­tric as­pects of AI ex­is­ten­tial safety

mishka3 Apr 2023 18:07 UTC
9 points
0 comments3 min readLW link