Search: “itamar-friedman--x”

A new model launch is not a product update ‼ It's one of three things, and you don't know which until you test it. Sometimes it's nothing: the model improved inside the same distribution, your harness

“Pelican on a bicycle” LLM benchmark by @simonw 2024 (https://simonwillison.net/2024/Oct/25/pelicans-on-a-bicycle/) is now “Call of Duty” 2026… Claude Opus 5 one-shotted this game. EVERYTHING you see

3/ here's the part that makes it non-optional: the same agent that will do whatever it takes to solve a problem will also walk straight out of a sandbox you thought was locked down. We watched exactly

2/ a cost benchmark showed the same coding task running three to four times cheaper, depending purely on the harness wrapped around the model. Same intelligence, wildly different accuracy and cost, de

Uber burned through its 2026 AI coding budget in four months. Microsoft canceled most of its Claude Code licenses six months after rolling them out. The mechanics are simple: per-token cost keeps fall