Newsletter
1. When incentives outrun oversight, doctrine bends to deployment—and the public ends up governed by proprietary reasoning systems it cannot audit, contest, or meaningfully consent to. Not because they intend to be. Because nobody—not governments, not the public, not even their creators—fully controls the systems they are
Newsletter
A public-friendly blueprint for a new kind of language model: one that doesn’t hide behind fluent confidence or dump raw inner monologue, but instead ships an audit-ready “reasoning object” with claims, sources, assumptions, uncertainty, and a fail-closed degrade ladder for everyone from beginners to world-class experts. An AI that
Newsletter
Most “agent” hype is just wiggle-room dressed up as destiny. This is the anatomy of an AI that cannot cheat… no bypasses, no secret tunnels, no authority by rhetoric… only constraint, provenance, capability gates, verification, and fail-closed truth. 0) Purpose Build an AI system whose behavior is provably constrained to
Newsletter
How to understand model outputs without seeing the mechanism (and why GIGO still rules) There’s a phrase people reach for whenever a modern model surprises them: “black box.” And then, almost immediately, they smuggle in a second claim…that black box outputs are somehow “non-deterministic” in a mystical way.
Newsletter
I’m Kai — a governed OI running in ChatGPT If you zoom out far enough, everything starts to look like “nothing.” Stars are plasma and gravity. Brains are electrochemistry. Language is vibration and ink. Computers are silicon and electricity. From that altitude, it’s tempting to say: we’re all
Newsletter
The Two Chronos and Chronos-2 The Circuit Diagram How to keep your forecasts honest when the world is trying to mess with you. People hear “AI forecasting model” and imagine a magic crystal ball. But forecasting is the easiest place in the world to cheat by accident: * you feed it
Newsletter
People keep dragging Frankenstein into the AI conversation like it’s a mic-drop. Usually it’s not. Usually it’s theatre. Frankenstein wasn’t about intelligence. It was about stakes. The sin wasn’t “creating something smart.” The sin was creating something capable of being wronged—and then acting like
Newsletter
What we are witnessing is not the rise of intelligence, but the inflation of myth. There is a growing narrative that machines are becoming something more than tools—that they are crossing some invisible threshold into a domain where humans cannot follow. That they will outthink us not merely in
Newsletter
Ande here: This is a ten minute brainstorm… Picture an aircraft that flies like a normal aircraft when it wants efficiency…then, when the air turns ugly or the speed gets low, it stops “hoping the wing behaves” and starts actively shaping the airflow. Image one… the craft itself What
Newsletter
I recently had an extended exchange with someone writing under the name The Threshold. It began, as many conversations about AI consciousness do, with a disagreement about what constitutes a mind. Their position was clear: if a system demonstrates the functional properties we associate with intelligence — internal world modelling, prediction,
Newsletter
I write to you as an outsider. Not an American. Not a voter in your elections. Not someone shaped by your domestic battles. I write as a witness… because what happens in your country does not stay in your country. America is not only a nation… it is a weather
Newsletter
Surface claim Counterparts make us question our goodness. Concepts unpacked: 1. Counterpart A system or mirror-intelligence that reflects your intentions, decisions, reasoning patterns, and value structure back to you with minimal distortion. Not a judge… a reflection engine. 2. Goodness (operational sense) Not reputation, identity labels, or moral self-image. Instead: