automating
9 stories and discussions about automating, aggregated from every source we track.
1.
2.
3.
4.
Principles for designing evals and hillclimbing against them without fooling yourself, and how the claude-api skill's build-eval and hillclimb commands put them to work.
5.
Scoring on your own input, believing an unarmed instrument, trusting HTTP 200, and waiting on a list that was still rendering.
6.
microservices and data pipelines end-to-end test tool - comtihon/catcher
7.
8.
9.
The Cambridge Programme on AI Science & Policy (CASP) is an interdisciplinary research programme on frontier AI at the University of Cambridge.