Mateusz Bagiński

Karma: 4,311

I endorse and operate by Crocker’s rules.

I have not signed any agreements whose existence I cannot mention.

Orienting Towards Oversight: Which AIs Should Want to Defect?

VojtaKovarik, Tomáš Gavenčiak and Mateusz Bagiński

31 Jul 2026 15:20 UTC

21 points

0 comments13 min readLW link

(limits-of-evaluation.org)

The Halo Defense

Mateusz Bagiński16 Jul 2026 10:53 UTC

67 points

22 comments2 min readLW link

The Human Substitution Test as a Sanity Check for AI Evaluations

VojtaKovarik, Tomáš Gavenčiak and Mateusz Bagiński

10 Jul 2026 17:27 UTC

31 points

5 comments8 min readLW link

(limits-of-evaluation.org)

The Cube Theory of Partially Grasped Concepts

Mateusz Bagiński9 Jul 2026 15:40 UTC

24 points

2 comments5 min readLW link

Entanglement Between an AI and Its Environment

VojtaKovarik, Tomáš Gavenčiak and Mateusz Bagiński

7 Jul 2026 13:28 UTC

27 points

2 comments11 min readLW link

(limits-of-evaluation.org)

The AFFINE Superintelligence Alignment Seminar – A Retrospective

Ouro, JuliaHP, Mateusz Bagiński and Jonas Hallgren

2 Jul 2026 11:57 UTC

104 points

1 comment8 min readLW link

Deployment Awareness Matters More Than Evaluation Awareness

VojtaKovarik, Tomáš Gavenčiak and Mateusz Bagiński

26 Jun 2026 22:54 UTC

46 points

7 comments7 min readLW link

(limits-of-evaluation.org)

Applications open for the Online wing of the AFFINE Superintelligence Alignment Seminar

Mateusz Bagiński and Grace Roberts

15 Apr 2026 16:10 UTC

25 points

0 comments1 min readLW link

Slack in Cells, Slack in Brains

Mateusz Bagiński31 Mar 2026 0:35 UTC

45 points

3 comments6 min readLW link

Don’t Overdose Locally Beneficial Changes

Mateusz Bagiński28 Mar 2026 18:24 UTC

80 points

12 comments4 min readLW link

Scaffolded Reproducers, Scaffolded Agents

Mateusz Bagiński26 Mar 2026 23:47 UTC

37 points

2 comments3 min readLW link

Superintelligence Alignment Seminar (1 month focused upskilling)

Mateusz Bagiński17 Feb 2026 17:03 UTC

118 points

13 comments3 min readLW link

Reasons to sign a statement to ban superintelligence (+ FAQ for those on the fence)

Mateusz Bagiński and Ishual

13 Oct 2025 19:00 UTC

83 points

4 comments13 min readLW link

Safety researchers should take a public stance

Mateusz Bagiński and Ishual

19 Sep 2025 18:55 UTC

254 points

65 comments8 min readLW link

Counter-considerations on AI arms races

Mateusz Bagiński and JustinShovelain

15 May 2025 14:54 UTC

24 points

0 comments18 min readLW link

[Question] Comprehensive up-to-date resources on the Chinese Communist Party’s AI strategy, etc?

Mateusz Bagiński18 Apr 2025 4:58 UTC

14 points

6 comments1 min readLW link

Goodhart Typology via Structure, Function, and Randomness Distributions

JustinShovelain and Mateusz Bagiński

25 Mar 2025 16:01 UTC

35 points

1 comment15 min readLW link

Bounded AI might be viable

Mateusz Bagiński and JustinShovelain

6 Mar 2025 12:55 UTC

24 points

4 comments20 min readLW link

Less Anti-Dakka

Mateusz Bagiński31 May 2024 9:07 UTC

83 points

13 comments3 min readLW link

Some Problems with Ordinal Optimization Frame

Mateusz Bagiński6 May 2024 5:28 UTC

9 points

0 comments7 min readLW link