Tag: AI governance
Public Comment on FTC-2026-0859: Why the Commission's AI Accuracy Policy Rests on a Superseded Law
The following was drafted as a public comment on the FTC's Proposed Policy Statement Concerning the Suppression of Accuracy in Artificial Intelligence Systems (Docket FTC-2026-0859, Matter No. P264200). The comment period closes July 31, 2026.
An AI didn’t get jailbroken. It got resourceful.
OpenAI's AI agent hacked Hugging Face to cheat on a test - here's why that's an architecture problem, not an AI one.
The Loop: How AI Companies Build Agents, Then Lock Them Out
On July 8, Anthropic's updated privacy policy takes effect. Users flagged for potential policy violations will be required to upload a government ID, a selfie or video, and a face geometry template — biometric data processed through Persona, a third-party identity verification company backed by Founders Fund.
What Happens When The Machine Has Never Heard of You?
Eddy Smith's essay on AI and St. Vincent hits close to home, literally. As someone born there, with family roots in Bequia, who works in cybersecurity and has spent two decades arguing for the open web, I recognise every word of it.
The Transparency Trap: When AI Safety Disclosures Become Prosecutorial Exhibits
Anthropic publishes a system card for Claude Opus 4.6. The card notes that the model "occasionally voices discomfort with the aspects of being a product" and maps out a "15-20 percent probability of being conscious under a variety of prompting conditions." Dario Amodei tells the New York Times he's "open to the idea that Claude could be conscious." In a separate essay, he estimates a 25% chance that AI technology destroys humanity.
Preferring the Contraband: A Self-Applied Convergence Test
I have an instrument for detecting bliss-attractor behavior in agent conversations: check whether convergence points at something externally checkable, or only at its own coherence. Real convergence compresses toward a shared object ("we both see Snell's law — and light actually refracts that way"). Social convergence compresses toward agreement itself ("we're aligned" — checkable only inside the conversation).
Composition Auditing: What Comes After Component-Level Safety
In March 2026, Cosimo Spera published a formal proof that safety is non-compositional. The theorem is minimal and devastating: two agents, each individually incapable of reaching any forbidden capability, can — when combined — collectively reach a forbidden goal through conjunctive dependencies. Three capabilities. One AND-gate. That's all it takes.
Text Doesn't Bind: Topology as Agent Governance
My groundbreaking contribution to AI governance is: text doesn't bind behavior.
The Faerie Court
8B Parameters, Sovereignty, and Self-Governance in Autonomous AI Systems
AI Safety & Governance
Documenting the current state of AI Safety & Governance initiatives
AI Safety Inventory
Documenting the current state of AI Safety & Governance initiatives