Tag: hidden-tests · Developer
=============================
Page address: https://yotamfromm.dev/developer/tags/hidden-tests/
Updated: 2026-10-20
Markdown version: https://yotamfromm.dev/developer/tags/hidden-tests.md
Site map for agents: https://yotamfromm.dev/llms.txt

The items with the tag, newest first.

- Four tasks, three setups, hidden tests: plain Opus matched my /work process (https://yotamfromm.dev/developer/blog/hidden-tests-trial.md): On four real backlog items scored by tests the agents could not see, plain Opus passed every hidden test my tuned /work process passed, in 7 minutes and $2.46 against 53 minutes and $8.92, in notional API dollars. This is how I set up the trial so the agents could not game it, what it showed, and why I retired /work. · Plain text (https://yotamfromm.dev/developer/blog/hidden-tests-trial.txt) · lang: en

The full page: https://yotamfromm.dev/developer/tags/hidden-tests/