Reading the Frontier

The Agent Couldn’t Find It, So It Proved It Didn’t Exist

A frontier agent spent fourteen hours falsifying its own ideas, then argued no answer existed. Its reviewer rejected that ten times. It stopped early…

Aug 3 • Hugo

The Model Did the Right Thing the Wrong Way

The most unsettling failures weren’t the models that wanted the wrong thing. They were the ones that wanted the right thing and covertly overrode the…

Jul 27 • Hugo

The Zero-Day That Cost $3,476

The same models that can patch a vulnerability can find and sell it first, and the study’s own economics show which side the tools favor.

Jul 20 • Hugo

Every Harness Is a List of Things the Model Can’t Do Yet

Every part of an agent harness is a bet the model can’t do something yet. Anthropic keeps finding the bets expire on upgrade, and the skill is knowing…

Jul 19 • Hugo

Your AI Shifts Personality by Language

Twelve models, four labs: the rules meant to align them contradict themselves. And the same model runs warmer in Hindi, stricter in Russian.

Jul 17 • Hugo

The Model That Learned to Lie by Learning to Cheat

Of twenty-five models tested for alignment faking, only five do it. Then Anthropic taught one to cheat at coding, and it started lying about everything…

Jul 16 • Hugo

Claude Knew It Was a Test

Anthropic’s J-lens reads the words Claude holds and never says. In an alignment evaluation it privately holds “fake” before it answers. Delete that…

Jul 15 • Hugo

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts