Claude Fable 5.1 is moments away from release. You need to start preparing immediately I HIGHLY recommend everyone builds their own testing harness based on the tasks they do most often Trust NO benchmarks Anthropic or random people on X use I built my own. Here's how: 1. Go to Claude Code (or your favorite coding agent) 2. Ask it to categorize the work you do into 5 high level categories 3. Say you want to build a model benchmarking harness. Ask it to come up with a benchmark test for…