Martín Soto

Karma: 1,359

Doing AI Safety research for ethical reasons.

Leave me anonymous feedback.

I operate by Crocker’s Rules.

Tell me about yourself: LLMs are aware of their learned behaviors

Martín Soto and Owain_Evans

22 Jan 2025 0:47 UTC

127 points

5 comments6 min readLW link

Near- and medium-term AI Control Safety Cases

Martín Soto23 Dec 2024 17:37 UTC

9 points

0 comments6 min readLW link

The Information: OpenAI shows ‘Strawberry’ to feds, races to launch it

Martín Soto27 Aug 2024 23:10 UTC

145 points

15 comments3 min readLW link

The need for multi-agent experiments

Martín Soto1 Aug 2024 17:14 UTC

43 points

3 comments9 min readLW link

OpenAI releases GPT-4o, natively interfacing with text, voice and vision

Martín Soto13 May 2024 18:50 UTC

54 points

23 comments1 min readLW link

(openai.com)

Conflict in Posthuman Literature

Martín Soto6 Apr 2024 22:26 UTC

40 points

1 comment2 min readLW link

(twitter.com)

Comparing Alignment to other AGI interventions: Extensions and analysis

Martín Soto21 Mar 2024 17:30 UTC

7 points

0 comments4 min readLW link

Comparing Alignment to other AGI interventions: Basic model

Martín Soto20 Mar 2024 18:17 UTC

12 points

4 comments7 min readLW link

How disagreements about Evidential Correlations could be settled

Martín Soto11 Mar 2024 18:28 UTC

11 points

3 comments4 min readLW link

Evidential Correlations are Subjective, and it might be a problem

Martín Soto7 Mar 2024 18:37 UTC

26 points

6 comments14 min readLW link

Why does generalization work?

Martín Soto20 Feb 2024 17:51 UTC

43 points

16 comments4 min readLW link

Natural abstractions are observer-dependent: a conversation with John Wentworth

Martín Soto12 Feb 2024 17:28 UTC

39 points

13 comments7 min readLW link

The lattice of partial updatelessness

Martín Soto10 Feb 2024 17:34 UTC

23 points

5 comments5 min readLW link

Updatelessness doesn’t solve most problems

Martín Soto8 Feb 2024 17:30 UTC

130 points

45 comments12 min readLW link

Sources of evidence in Alignment

Martín Soto2 Jul 2023 20:38 UTC

20 points

0 comments11 min readLW link

Quantitative cruxes in Alignment

Martín Soto2 Jul 2023 20:38 UTC

19 points

0 comments23 min readLW link

Why are counterfactuals elusive?

Martín Soto3 Mar 2023 20:13 UTC

14 points

6 comments2 min readLW link

Martín Soto’s Shortform

Martín Soto11 Feb 2023 23:38 UTC

3 points

46 comments1 min readLW link

The Alignment Problems

Martín Soto12 Jan 2023 22:29 UTC

20 points

0 comments4 min readLW link

Brute-forcing the universe: a non-standard shot at diamond alignment

Martín Soto22 Nov 2022 22:36 UTC

9 points

2 comments20 min readLW link