AI safety researcher turned founder. I spent years deep in alignment work, from SERI MATS to leading the Supervising AIs Improving AIs research agenda to building tools that accelerate safety researchers. Previously a data scientist and physicist.
I blog at Aligned to Flourish about AI safety, building in the age of agents, and the future of software.
Recent
When Execution Gets Cheap, Does Taste Become the Moat?
Hard Truths About Where AI Is Headed
Difficulties in Building an AI Safety Startup
Gaining Clarity on Automated Alignment Research
Better Model Diffing Is Needed
Automating AI Safety: What We Can Do Today
AI Alignment
AI Alignment Project Ideas
Accelerating AI Alignment Research (Talk)
Using Data Attribution for AI Alignment
A Descriptive Overview of Current AI Alignment Research
Miscellaneous
How Much I'm Paying for AI Productivity Software
The Importance of Entropy
Quantum Computing, Photonics, and Energy Bottlenecks for AGI
GitHub Stats