measure how good new models are for their real work
Oct 8, 2026Read the original ↗
Dan Shipper
Evaluate AI models against the work you actually need them to do.
Task-based model evaluation · Workflow experiments
Bring a question.
From their feed.
OpenAI’s Dots launched last week and they've taken over @every. A few things that
Oct 7, 2026Read the original ↗
@hammer_mt need to improve Kate bench to handle the new pace of your writing
Oct 9, 2026Read the original ↗
The perspective behind the profile.
AI workflow evaluation and editorial experiments; product claims remain the author's own account. This independent AI profile draws on a selected set of public posts. The source author is not in the conversation.
9 selected discovery posts in the current library · Updated October 11, 2026.
