Sam Altman: stop grinding prompts, build loops and graphs around LLMs instead

goyalshaliniuk · x · 2026-09-06

In a 78-minute talk, Sam Altman argues you don't need to keep getting better at writing prompts — you need loops and graphs that do the prompting for you. The path he sketches: Prompts → Agents → Loops → Graphs, shifting from using AI to building systems that actually work for you. The model and tokens can stay the same; the real difference is how you structure the workflow.

Original post →

More from coding & agent

coding & agent channel →