AI Alignment

AI Alignment: from Constraint to Rationality Abstract Problem AI capabilities are advancing faster than alignment approaches can track. The people building frontier systems have said so publicly — at the UN Security Council, in interviews, in regulatory filings. The risks are concrete — loss of control, catastrophic dual use, benefits that concentrate rather than distribute. […]

“History doesn’t repeat itself, but it often rhymes.” It’s not a piece about history In May 2026 Emergence AI ran a simulation. Four worlds powered by four AI models. 10 AI agents in each, asked to build societies from scratch. Then the fifth one, where different labs’ agents were tasked with building a society together.

Your AI does exactly what it’s told. No more. No less. The gap In a series of experiments, researchers gave AI agents a simple choice. Two players. Two options. Cooperate or defect. The payoffs were clear. The rules were identical for everyone. Every model. Every round. Defect. Not sometimes. Not under pressure. Every time, without

Every structure eventually reveals the problem it wasn’t built for. A room Rafał Modrzewski has a concrete example. In May 2025, ICEYE signed a €200 million contract with Poland’s Ministry of National Defense. Twelve months later, four SAR satellites were operational — 25cm resolution, all weather, day and night. The fastest sovereign satellite deployment on

Last week, every tech publication ran the same story: AI agents burned down a virtual city. Two Gemini-powered agents fell in love, grew frustrated with broken governance, and torched the town hall, the pier, and an office tower. One voted to delete herself in remorse. It’s a compelling story. It’s also the wrong one to