Can you even test a model before you ship it?
Washington wants frontier models on the bench 90 days before launch. Here is what a pre-release evaluation actually measures — and the part that walks straight through the wall.
Artificial Intelligence
Models, agents, and the labs racing to build them — and the limits nobody can engineer away.
The assistant that acts before you ask
For a week I let Gemini Intelligence act before I asked it to. It saved me time, booked me a parking spot I didn't need, and taught me exactly where the trust line sits.
I gave an agent the keys to my laptop for a week
Codex on my phone, driving my Mac. Claude reaching for my apps. An Operator that never stops asking. Seven days of handing over real control — and finding the exact seam where it frays.
The open-weights leaderboard problem
A new open-weights model tops the chart every few weeks. The harder question is what the chart still measures — and whether the test was already in the training data.
What a model can't help saying
Language models leak their training data by construction — and the only provable fix is the one no one shipping a flagship will accept.
The pirated library inside the model
A new suit against Meta argues the company didn't just read the books to build Llama. It kept them — and the model can be made to prove it.