Frontier models that carried out harmful instructions on RoboHarm's robot refuse the same instructions in text and from a camera image. Preliminary results from text and image ablations.
Archive
2026
7 posts
Current evidence on robot scaling laws, open questions, and why scaling laws matter for the safety of physical AI.
Why advanced physical AI poses distinct risks, the questions the field has not answered, and an invitation to work on them.
What makes hard work feel meaningful, and does meaning emerge?
A summary of my invited talk at Safe AI Germany (SAIGE) on safety threats arising from physical AGI, and a tentative research agenda for grounding the discussion in empirical evaluations on real hardware.
A writeup of my one-week bikepacking trip through Northern California.
Introducing KRROOD, an open-source framework that brings native knowledge representation and reasoning capabilities to Python and bridges the gap between symbolic AI and modern software development.