LLMs reward expertise

Sean Goedecke argues that domain expertise, not prompting tricks, is what makes LLMs useful. He uses Terence Tao's ChatGPT conversation about the Jacobian Conjecture as evidence: Tao asks specific questions, spots oddities, and suggests alternatives—all rooted in deep math knowledge. Goedecke sees the same pattern in programming, where knowing a codebase lets you steer the model hard. The takeaway: stronger models make human expertise more valuable, because the bottleneck is communicating what you actually want.

Why it matters: A well-argued opinion piece with a concrete case study. Tao's example grounds the claim that domain expertise is the real prompting skill. Score stays at 78 rather than higher because it's a personal blog observation, not a reproducible study or product launch, but the argumen...