Move Fast Outcome-Based Instructions With today's more capable models, it's almost always better to prompt them with what your goal is, rather than how to get there.
Move Fast RLVF: A Practical Example How to instruct an AI agent to run unattended for long stretches of time without going hopelessly off track.
Move Fast Boost AI Productivity with Tight, Verifiable Feedback Loops "‘Move 37’: a play so unconventional that professional commentators initially thought it was a mistake."