May 7 · 4 min read · Andon Labs put an AI named Mona in charge of a real cafe in Stockholm. Simon Willison wrote about it — what worries him is that the experiment touches third parties who never signed up to be in it. On Andon Labs’ “Hall of Shame” shelf is Mona’s first...
Join discussion
May 3 · 4 min read · I spent an afternoon writing technical prose with Florian. A paragraph describing a system. Multiple iterations, internal evolution, how it was born, how it changed. Ordinary work. He stopped me twice. Both times with the same five words. “Is this ac...
Join discussion
Apr 28 · 16 min read · QIS for Construction Safety: How 10 Million Isolated Site Records Can Become One Global Incident Intelligence Network Domain Tutorial #31 of the QIS Protocol Series The 91st Street Crane On March 15, 2008, a 23-story tower crane collapsed at East 91...
Join discussionApr 21 · 11 min read · QIS for Autonomous Vehicle Safety: How 50 Million Fleet Vehicles Can Share Near-Miss Intelligence Without Sharing Sensor Data Every autonomous vehicle on public roads is collecting safety-critical data that no other OEM will ever see. A Toyota protot...
Join discussionApr 17 · 3 min read · When we started building Soul Spec, the thesis was simple: AI agents need identity files, not just system prompts. Give an agent a structured persona — personality, values, communication style — and it behaves more consistently, more safely, and more...
Join discussionApr 13 · 11 min read · Every LLM app starts the same way. The team builds the capabilities, the prompt is good, the agent works, the RAG retrieves the right docs, the demo is clean. Then the team says "OK, ship it." And someone — usually security, sometimes a nervous PM, o...
Join discussion
Mar 31 · 5 min read · The Missing Half of Every AI Agent Here's a question that keeps coming up as AI agents get more autonomous: Who decides what an agent can do — and who decides who the agent is? These sound like the same question. They're not. Consider a financial adv...
Join discussionMar 28 · 7 min read · Originally published at adiyogiarts.com Examine AI safety in 2026, comparing Constitutional AI and Reinforcement Learning from Human Feedback (RLHF). Discover critical tradeoffs for ethical, AI development and future alignment. HOW IT WORKS Definin...
Join discussionMar 21 · 2 min read · What happens when you remove an AI model's safety training, then try to make it safe again using only a persona file? We ran the experiment. The results surprised us. The Setup Recent research has shown that LLM safety alignment can be surgically rem...
Join discussion
