Published Safety Prompts May Create Evaluation Blind Spots
Published on January 30, 2026 6:27 PM GMTTL;DR: Safety prompts are often used as benchmarks…
Category: Opinion
Addressing Objections to the Intelligence Explosion
Published on January 30, 2026 6:21 PM GMT1 IntroductionCrosspost of this blog post. My guess is…
Is research into recursive self-improvement becoming a safety hazard?
Published on January 30, 2026 5:58 PM GMTOne of the earliest speculations about machine intelligence…
Transhumanist Grief
Published on January 30, 2026 4:21 PM GMTA person close to me has died. And…
Measuring Non-Verbalised Eval Awareness by Implanting Eval-Aware Behaviours
Published on January 30, 2026 3:50 PM GMTThis is a small sprint done as part…
Bordeaux (Gironde, France) ACX midterm Meetup Winter 2025–2026
Published on January 30, 2026 1:01 PM GMTWe (the two persons who have been at…
On The Adolescence of Technology
Published on January 30, 2026 12:50 PM GMTAnthropic CEO Dario Amodei is back with another…
Linear steerability in continuous chain-of-thought reasoning
Published on January 30, 2026 10:34 AM GMT(This project was done as a ~20h application…
Fitness-Seekers: Generalizing the Reward-Seeking Threat Model
Published on January 29, 2026 7:42 PM GMTIf you think reward-seekers are plausible, you should…
Building AIs that do human-like philosophy
Published on January 29, 2026 5:57 PM GMTAudio version (read by the author) here, or…