Dev: If You Don't Routinely YOLO Big Open-Ended Tasks to Frontier Models, Your AI Priors Are Outdated

brandon_galang · x · 2026-11-17

Developer Brandon Galang argues that if you aren't routinely throwing big, open-ended tasks across different domains at the newest frontier models in YOLO mode, your priors on what AI can do are significantly out of date — a sign frontier models now handle autonomous long-horizon work far better than most users assume.

Original post →

More from coding & agent

coding & agent channel →