Artificial Intelligence
The Constitution That Never Happened
The public does not arrive at the moment of authorization. It arrives at the moment of malfunction.
Artificial Intelligence
Artificial Intelligence
What the Benchmark Cannot See
AI progress became publicly visible through benchmarks: scores, leaderboards, deltas, and claims that could travel. But every machine for seeing intelligence also teaches us what not to see. Benchmarks make capability legible by removing variance. Deployment brings the excluded world back.
Artificial Intelligence
Verification Inside the Swarm
What changes when verification stops standing outside the loop? Swarm architectures do not just distribute action. They distribute judgment, making authority more ambient, authorship harder to trace, and the human harder to locate.
Artificial Intelligence
The Loop is the System
The deeper question is whether the surrounding process can recognize that successor as better, distinguish gain from drift, and make the gain stick.
Artificial Intelligence
The Physicalization of Intelligence
Elon Musk’s terawatt-scale fab announcement is easy to read as a familiar escalation: more chips, more power, more compute. Recent reporting around Musk’s Terafab plans and Tesla’s chip-production timeline gives that announcement a sharper edge than ordinary scale theater. But that framing is already too shallow. The
Artificial Intelligence
The Reliability Gap
The most expensive AI failures may not come from systems that fail often, but from systems that fail rarely enough to be trusted. Large language models have become useful enough to invite dependence before becoming reliable enough to deserve it.