RSS

Ihor Kendiukhov

Karma: 1,602

I have rather Yudkowskian views on the alignment problem. I think we need to go hard on biology and am trying to contribute to that with my biomechinterp work. I am doing volunteer AI safety research at https://​​www.theomachialabs.com.

I come from what I call “classical transhumanism background”.

More about me: https://​​linktr.ee/​​kendiukhov

Open Prob­lems in Mechanis­tic In­tepretabil­ity of Biolog­i­cal AIs

Ihor Kendiukhov14 Aug 2026 15:35 UTC
19 points
0 comments2 min readLW link

The En­tan­gled Di­men­sions of De­ci­sion Theory

Ihor Kendiukhov30 Jul 2026 15:23 UTC
38 points
3 comments42 min readLW link

The Banal­ity of Takeoff

Ihor Kendiukhov12 Jul 2026 13:45 UTC
28 points
18 comments3 min readLW link

A For­mula for Fun

Ihor Kendiukhov30 May 2026 13:01 UTC
11 points
3 comments8 min readLW link

Sparse Au­toen­coders for Sin­gle-Cell Models

Ihor Kendiukhov12 Apr 2026 16:07 UTC
36 points
2 comments6 min readLW link

AI Doom Markets

Ihor Kendiukhov8 Apr 2026 19:41 UTC
14 points
1 comment1 min readLW link

Com­pute Curse

Ihor Kendiukhov4 Apr 2026 14:47 UTC
20 points
6 comments5 min readLW link

We Need Pos­i­tive Vi­sions of the Future

Ihor Kendiukhov2 Apr 2026 13:19 UTC
20 points
6 comments7 min readLW link

The Eve of Gen­tle Sin­gu­lar­ity: A Short Story

Ihor Kendiukhov1 Apr 2026 8:21 UTC
22 points
0 comments4 min readLW link

My One-Year-Old Pre­dic­tions for What the World Will Look Like in 3 Years

Ihor Kendiukhov30 Mar 2026 13:56 UTC
12 points
2 comments3 min readLW link

Com­ing of Age: Chap­ters 1 and 2

Ihor Kendiukhov24 Mar 2026 9:15 UTC
13 points
0 comments1 min readLW link

My Most Costly Delusion

Ihor Kendiukhov22 Mar 2026 12:21 UTC
157 points
14 comments3 min readLW link

The Case for Low-Com­pe­tence ASI Failure Scenarios

Ihor Kendiukhov19 Mar 2026 23:10 UTC
144 points
8 comments6 min readLW link

Re­quiem for a Tran­shu­man Timeline

Ihor Kendiukhov17 Mar 2026 21:27 UTC
280 points
46 comments5 min readLW link

What are the best ways to pub­lish ra­tio­nal fic­tion nowa­days?

Ihor Kendiukhov16 Mar 2026 18:13 UTC
17 points
15 comments3 min readLW link

Less Ca­pable Misal­igned ASIs Im­ply More Suffering

Ihor Kendiukhov15 Mar 2026 9:36 UTC
9 points
3 comments6 min readLW link

Ex­tract­ing Perfor­mant Al­gorithms Us­ing Mechanis­tic Interpretability

Ihor Kendiukhov14 Mar 2026 14:19 UTC
57 points
7 comments7 min readLW link

The Lethal Real­ity Hypothesis

Ihor Kendiukhov11 Mar 2026 15:23 UTC
107 points
25 comments20 min readLW link

On The In­de­pen­dence Axiom

Ihor Kendiukhov8 Mar 2026 14:38 UTC
343 points
92 comments23 min readLW link

Mechanis­tic In­ter­pretabil­ity of Biolog­i­cal Foun­da­tion Models

Ihor Kendiukhov20 Feb 2026 18:01 UTC
34 points
1 comment26 min readLW link