LESSWRONG
LW

Zach Stein-Perlman
9670Ω3228262412
Message
Dialogue
Subscribe

AI strategy & governance. ailabwatch.org. ailabwatch.substack.com. 

Sequences

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
Slowing AI
ryan_greenblatt's Shortform
Zach Stein-Perlman12h40

Update: experts and superforecasters agree with Ryan that current VCT results indicate substantial increase in human-caused epidemic risk. (Based on the summary; I haven't read the paper.)

Reply
Kabir Kumar's Shortform
Zach Stein-Perlman3d253

this is evidence that tyler cowen has never been wrong about anything

Reply13
Substack and Other Blog Recommendations
Zach Stein-Perlman5d40

Two blogs that regularly have some such content are Transformer and Obsolete.

Reply
Substack and Other Blog Recommendations
Zach Stein-Perlman5d293

Pitching my AI safety blog: I write about what AI companies are doing in terms of safety. My best recent post is AI companies' eval reports mostly don't support their claims. See also my websites ailabwatch.org and aisafetyclaims.org collecting and analyzing public information on what companies are doing; my blog will soon be the main way to learn about new content on my sites.

Reply
No, Futarchy Doesn’t Have an EDT Flaw
Zach Stein-Perlman8d42

I don't understand the footnote.

In 99.9% of cases, the market resolves N/A and no money changes hands. In 0.1% of cases, the normal thing happens.

What's wrong with this reasoning? Who pays for the 1000x?

Reply
No, Futarchy Doesn’t Have an EDT Flaw
Zach Stein-Perlman8d50

Yes but this decreases traders' alpha by 99.9%, right? At least for traders who are constrained by number of markets where they have an edge (maybe some traders are more constrained by risk or something).

Reply1
AI companies' eval reports mostly don't support their claims
Zach Stein-Perlman12d20

Coda: Anthropic published https://www.anthropic.com/research/agentic-misalignment

Reply
The Best Reference Works for Every Subject
Zach Stein-Perlman12d122

Domain: AI safety from the perspective of what AI companies are doing and should do

Links: AI Lab Watch and AI Safety Claims Analysis

Author: Zach Stein-Perlman

Type: website

Reply
ryan_greenblatt's Shortform
Zach Stein-Perlman24d90

Anthropic's model cards . . . . are substantially more detailed and informative than the model cards of other AI companies.

My weakly-held cached take is: I agree on CBRN/bio (and of course alignment) and I think Anthropic is pretty similar to OpenAI/DeepMind on cyber and AI R&D (and scheming capabilities), at least if you consider stuff outside the model card (evals papers + open-sourcing the evals).

Reply1
AI companies' eval reports mostly don't support their claims
Zach Stein-Perlman24d31

Alignment and capabilities are separate. 

Welcome to the forum! No worries. 

Reply
Load More
4Zach Stein-Perlman's Shortform
Ω
4y
Ω
243
33Epoch: What is Epoch?
8d
1
16AI companies aren't planning to secure critical model weights
12d
0
205AI companies' eval reports mostly don't support their claims
Ω
1mo
Ω
12
58New website analyzing AI companies' model evals
1mo
0
72New scorecard evaluating AI companies on safety
1mo
8
71Claude 4
1mo
24
36OpenAI rewrote its Preparedness Framework
3mo
1
241METR: Measuring AI Ability to Complete Long Tasks
Ω
3mo
Ω
106
33Meta: Frontier AI Framework
5mo
2
53Dario Amodei: On DeepSeek and Export Controls
5mo
3
Load More
Ontology
2y
(+45)
Ontology
2y
(-5)
Ontology
2y
Ontology
2y
(+64/-64)
Ontology
2y
(+45/-12)
Ontology
2y
(+64)
Ontology
2y
(+66/-8)
Ontology
2y
(+117/-23)
Ontology
2y
(+58/-21)
Ontology
2y
(+41)
Load More