Fork Around and Find Out Part 2: One Head does the Summing
Summary of this postThis is the second in a series of posts detailing my manifold findings while investigating how a chess transformer engine that mimics human…
Summary of this postThis is the second in a series of posts detailing my manifold findings while investigating how a chess transformer engine that mimics human…
Most AI control research such as LinuxArena and Ctrl-Z only gives the red team basic agents which only have access to tools. Yet in 2026, usage…
It’s a quiet week so let’s do the monthly right on schedule. Table of Contents Bad News. Good Advice. Opportunity Knocks. While I Cannot Condone This.…
SummaryNeural networks are widely assumed to use superposition to represent more features than they have dimensions. A stronger claim is that they also compute in superposition…
Aleksandr Bowkis* and David Africa*TL;DRChain of thought (CoT) monitorability may be fragile, and natural language autoencoders (NLAs) may provide a helpful, decorrelated monitoring surface.We tried to…
This is a follow-up to "Have You Tried Thinking About It As Crystals?" because apparently I wasn't done. Beware that this one is a bit out…
Thinking about "Plan A" makes me want to make concrete proposals towards those goals.I think Anthropic's "Project Glasswing" provides a clear and easily implemented first-step policy…
This post was originally posted my Substack. I can be reached on LinkedIn and X.Just when it seemed that the frontier AI battle was a two-horse…
An export-control order in June exposed the real problem—and why Europe's regulatory toolkit can't fix it. [1]The most important AI-governance development of 2026 so far wasn’t…
ForewordWe will continue where we left off. In the last post, I introduced a few important observables along with the setup. We are interested in their…