Childhood and Education #20: Phones and Screens
We have a respite, so I thought I’d tackle various thoughts on children, phones and screens. GPT-5.6-Sol drops tomorrow, and the Fable agents are hard at…
Latest
Can the U.S. and China Deny AI?
Summary: Right now, we have no idea how practical it is for countries to sabotage each others’ AI projects. This makes it hard to forecast what…
A Real-Life Example of an Aligned System Killing Hundreds of People
I wrote this piece while at the AFFINE Superintelligence Alignment Seminar during discussions about the difference between AI Alignment and AI Safety. If you’re simply interested…
Subliminal Learning Happens at Every Rank, Given the Right Learning Rate and Enough Data
Subliminal learning is the phenomenon where a language model picks up a behavioral trait—such as fondness for cats—by training on data from a trait-carrying teacher that…
AI Safety at the Frontier: Paper Highlights of May & June 2026
tl;drPaper of the month:Anthropic’s Jacobian lens reveals that models have a sparse workspace of verbalizable concepts that causally carries multi-hop reasoning and surfaces hidden cognition —…
Why study proto-training gaming as an adversarial alignment failure mode?
This is a dual post that lays out our current research project where we compare different pre-RL alignment methods and their ability to prevent models from…
Why study alignment interventions on pre-RL checkpoints?
This is a dual post that lays out our current research project where we compare pre-RL-training methods on their ability to prevent models from ‘proto-training gaming,’…
Artificial Ambassadors: The Three Cases for Sending LLMs to Deep Space
For something that “simply predicts the next token”, Large Language Models are a surprisingly versatile technology. In addition to the obvious applications, such as chatbots, translation…
Reframing LessWrong-style decision theory as "commitment theory"
Thanks to @eigengender and especially Chris Lakin and Simon Dima for valuable comments on a draft.In this post, I will present an alternate framing[1] of LessWrong-style…
Why I'm a moral anti-realist but may be unable to convince you
Figure from Chapter 4 of Understanding Knowledge by Michael HuemerOn a high level there aren’t that many ways knowledge can be justified (or not). This figure…