Information work is bottlenecked by high-signal context more than by inference
by delifue on 3/10/2025, 1:43:36 AM
This kind of explains why LLMs are good at making demos and good at writing code under clear specification, but often break existing features in a large codebase. When codebase become large, the signal-to-noise ratio of context reduces.
This kind of explains why LLMs are good at making demos and good at writing code under clear specification, but often break existing features in a large codebase. When codebase become large, the signal-to-noise ratio of context reduces.