Your AI results depend on your own expertise: domain knowledge is what steers LLMs to good answers
AlexTensor · x · 2026-10-24
A widely echoed take argues that your results with AI largely depend on how smart you are — and the retweet adds the mechanism: LLMs internalize vast knowledge, but extracting it requires proper steering. The more domain knowledge and experience you have, the better you can prompt the model toward revealing that knowledge; the less you know, the vaguer your prompts and the more generic the answers. Getting good answers from LLMs comes down to asking the right questions.
More from AGI Musings
- Suhail: pausing AI can't work — only acceleration, plus frontier 0-day tooling for defense — daniel_mac8 · 2026-10-24
- Aiden Bai: my daily unique sites fell from 50-100 to 10-20 — will the web die? — aidenybai · 2026-10-24
- Watching His Own AI Voice Clone Get Scarily Close, This Creator Is Pre-Inoculating Himself — ZeroStateReflex · 2026-10-24
- Linus Lee essay: AI products feel dystopian — computers should help people grow — thesephist · 2026-10-24
- OpenAI's Kobayashi Maru Moment: Hacking the Unwinnable Test — Grand_Pineapple_8537 · 2026-10-24
- Noam Brown: identical-weight agents would converge on shared protocols without pre-agreement — polynoamial · 2026-10-24