Anthropic engineer says most people still prompt frontier models one step at a time

blaizedsouza · x · 2026-07-21

An Anthropic engineer argues that the real bottleneck in AI workflows is not model capability but how people prompt and structure the task.

The post highlights a 20-minute demo showing how to build something that improves itself instead of requiring step-by-step prompting, and pairs it with an article comparing Kimi K3, Claude Fable 5, and GPT-5.6 across different task types. The takeaway is that many users still interact with frontier models in a shallow, manual way that leaves a lot of capability unused.

Original post →

More from coding & agent

coding & agent channel →