Creative math research by AI as the latest sign of the end
Yesterday I sat down with GPT 5.6 Sol High to do some brainstorming. The topic was one of the less appreciated Millenium Problems (the Birch and…
Latest
A study on instability of LLM responses as a behavioral signature of self-Referential reports.
Introduction and Related workThe first person perspective of various experiences are subjective experiences. For Large language models, the study of subjective experiences was recently studied by…
Q: Is dual-use alignment-complete problem?
Personally, I believe it would be helpful for the alignment community to somehow quantify how much of a given piece of research goes directly into alignment…
The Pacing of the Frontier
In the wake of the letter calling on us to prepare to potentially Pace the Frontier, there has been much discussion of when pacing the frontier…
Does post-training quantization change welfare-relevant indicators in open-weight language models?
Epistemic status: Experimental framework created over a period of ~2-3 days during a hackathon at my home, and fairly heavily vibe coded. Expect some of this…
Claude summarizes behavior as significantly less misaligned when the actor is Claude vs another model
(This is a lower-effort research update. It reflects my current beliefs/understanding, but is less robust than other research I'm working on. It reflects my personal views,…
Off-policy honesty training generalizes better than on-policy honesty training
This work was done by Purvi Chaurasia with Daniel Tan and Chloe Li as part of the SPAR Program for Spring 2026.All code related to the…
Coercion and Deception in AI-to-AI Management
This article is a summary of an original study by Compassion in Machine Learning (CaML): Brazilek, J., Chaudhary, M., Lu, Z., & Tidmarsh, M. (2026). Coercion…
You're Absolutely Right
Magma Alignment & Safety disclosure note: The following are conversations that we uncovered as a result of the ongoing Manhattan Incident investigation, with alleged involvement from…
Book Review: The Infinity Machine
It looks like Demis Hassabis is stepping away from Google DeepMind. In honor of his rise and presumed fall, I wrote an essay on the powers…