"In the hyperstitional model Kaye outlined, fiction is not opposed to the real. Rather, reality is understood to be composed of fictions—consistent semiotic terrains that condition perceptual, affective and behavioral responses." - Pdf The Cybernetic Cultural Research Unit, founded by Nick Land, was a group of social theorists and philosophers...
This is a research note presenting a portion of the research I did during MATS 8.0 under the supervision of Girish Sastry and Steven Adler. Tl;dr: I tested whether Claude Sonnet 4 would sabotage code when given goal conflicts (similar to the Agentic Misalignment paper), and whether it generates worse...
tl;dr: Many critiques of *Situational Awareness* have been qualitative; one year later we can check the numbers. I did my best to verify his claims using public data through June 2025, and found that his estimates mostly check out. Thanks to Kai Williams & Egg Syntax for their critical feedback....
"In the hyperstitional model Kaye outlined, fiction is not opposed to the real. Rather, reality is understood to be composed of fictions—consistent semiotic terrains that condition perceptual, affective and behavioral responses." - Pdf
The Cybernetic Cultural Research Unit, founded by Nick Land, was a group of social theorists and philosophers at the University of Warwick who wrote about the internet, society, and culture. I understand that LessWrongers are generally ontologically skeptical of these two groups, but Land and Ccru's ideas are the important thing here.
It's shocking to me how familiar Ccru ideas feel to LessWrongism, as well as many in the Rationalist-adjacent community. In general, it feels like Ccru/Land and LessWrong/Rationalism are social-science... (read 239 more words →)
This is a research note presenting a portion of the research I did during MATS 8.0 under the supervision of Girish Sastry and Steven Adler.
Tl;dr: I tested whether Claude Sonnet 4 would sabotage code when given goal conflicts (similar to the Agentic Misalignment paper), and whether it generates worse code for companies it 'dislikes.' In an AM-style scenario, Claude frequently sabotaged code, but in more realistic settings with subtle company information, there was no correlation between company preference and code quality.
Poster avaible here.
Motivation
In June, the Agentic Misalignment paper came out. Despite methodological debate surrounding the contrived-ness of the scenarios, the main finding of this paper, that agents will take ~catastrophically harmful actions under... (read 1347 more words →)
tl;dr: Many critiques of *Situational Awareness* have been qualitative; one year later we can check the numbers. I did my best to verify his claims using public data through June 2025, and found that his estimates mostly check out.
Thanks to Kai Williams & Egg Syntax for their critical feedback.
Abstract
Leopold Aschenbrenner’s 2024 essay Situational Awareness forecasts AI progress from 2024 to 2027 in two groups: "drivers" (raw compute, algorithmic efficiency, and post-training capability enhancements known as "un-hobbling") and "indicators" (largest training cluster size, global AI investment, chip production, AI revenue, and electricity consumption).[1] Drivers and the largest cluster size are expected to grow about half an order of magnitude (≈3.2×) annually, infrastructure indicators roughly... (read 3401 more words →)