~/tests
// tests
Tests
Tests are hands-on verdicts only. They prove whether a tool, feature, model, prompt or workflow holds up against a real task, with what worked, what broke and what would change the view.
Test · work
Claude Fable 5 vs GPT-5.6: Project Handover Review
GPT-5.6 produced the better steering-ready handover. Claude Fable 5 was stronger at challenging disputed approvals and conflicting evidence.
Test · work
ChatGPT vs Copilot in PowerPoint: the steering committee test
I gave ChatGPT and Copilot ten files of project mess and a locked committee deck. One edited the template perfectly. One signed my name to it. See the scores.
Test · work
Claude Sonnet 5 test: one call, two clean outputs
I gave Claude Sonnet 5 one messy transcript and asked for two clean outputs in one prompt. Read what worked, what broke, and whether it holds up on day one.
// the newsletter
Get each test when it lands.
Guides, templates, builds, tests and opinions for practical AI at work, at home and for play.
// no hype, no spam. unsubscribe whenever.