A 2001 film and a 2026 research paper are circling the same problem. We should be paying attention.Continue reading on Medium »
A study published yesterday in Science should make every developer building with LLMs stop and re-examine their pipelines.Continue reading on Towards AI »
Image by author in CanvaABSTRACTCurrent approaches to AI safety prioritize alignment — ensuring systems follow human values through reward optimization, constitutional constraints, and safety guidelines. While necessary, these methods may be fundamenta…
Moonbounce has raised $12 million to grow its AI control engine that converts content moderation policies into consistent, predictable AI behavior.
How separation of concerns, automated controls, and forward-looking assessment solve the same coordination problems for agents and humansThis is a follow-up to Governing the Ant Farm: A Governance-First Framework for Multi-Agent Software Delivery, publ…