Technology
Industry news, tooling and everything that does not fit a narrower box.
The Simulator Said 301. The Phone Said 155
Last month I counted 119 mistakes that got through because somebody checked the wrong thing. This is one more, caught in time. AI agents built the part of my library that runs a language model on the device itself, and they tested it on an iPhone simulator: 301 tokens a second. The real phone gave 155. The pretend Android phone was wrong in the other direction. Four real devices, one table of measured numbers, and what it taught me about the word "tested".
AI Put Me on a Pedestal. Then I Looked Down
I spent a year building software with AI, then built a tool to measure whether it was working. The first number it gave me was humbling. In eleven days it logged 268 misses, meaning things the AI got wrong or left out. My automated checks caught 46 of them. Agent reviews caught 82. I caught 122. By opening the app and clicking around, like it was 2010. The most common reason something slipped through, 119 times, was not that nobody checked. It was that somebody checked the wrong thing. And the worst number is the one I do not have. I only