The Case for Physical AI Safety
BackgroundThe AI safety field has spent a decade building tools for systems trained to think and digitally act. The next decade will likely deliver widely deployed…
Latest
Frontier AI lab misalignment risk, lessons from trading post-2008
In this post, I propose adapting banking risk management frameworks (specifically capital adequacy requirements like Basel III) to frontier AI labs. By forcing them to hold…
Does routine compression undo LLM unlearning? A short project
I completed this project over 2 weeks as part of a BlueDot Project cohort. It was my first solo project and I learned a lot! Feedback…
The AI Safety Illusion: Why Current Safety Datasets Fool Us on Model Safety
AI models are increasingly trained to be “safe,” meaning they refuse harmful requests. But what does it truly mean for a model to be safe? Today,…
Adderall Tolerance: Much More Than You Wanted To Know
The effectiveness of amphetamine (e.g. Adderall) and methylphenidate (e.g. Ritalin) for the symptoms of ADHD, that is, lack of executive function, has been demonstrated beyond reasonable…
Banana in, Bostrom out: paperclip maximization is one token-direction swap away (in Qwen 3.6-27B)
IntroductionI started learning about interpretability late February of this year. I’ve been a full stack dev for a non profit for a few years now, developing…
Attempt at Finding Alignment Faking on Llama 70B to test sleeper-agent detection generalizes
Epistemic status: empirical report from a 30-hour project sprint. Null result, reported honestly, with full code and data.TL;DR MacDiarmid et al. (2024) showed that a linear…
PauseCon London '26: Applications now open
We shared a post here recently arguing that existential AI safety needs an effective social movement. If you read that and found yourself agreeing, or wanting…
What do I mean by “Artificial General Intelligence”?
In this post,[1] intended for a broad audience, I will paint a brief picture of what I’m talking about when I talk about “AGI”. It will…
AI 2040: Is it Actually a Deal?
The "AI Futures Project" has released their AI 2040: Plan A scenario. While their previous scenario AI 2027 was a forecast of what they thought a…