A post of "174 characters" was actually 283 by X's official count — Japanese is 2 points per character, and URLs are 23 points regardless of length

Have you ever had an AI write a post for X (formerly Twitter) and posted it after being told, "It's under 140 characters" or ...
InfoQ

Android Bench 2 Adds Support for Long-Horizon Tasks, Agentic Evaluation, and Continuous Scoring

Google has released Android Bench 2.0, a major update to its benchmark framework for evaluating AI models and agents on Android development tasks. The update introduces long-horizon tasks (LHTs), ...