A perfect human: notes on making every LLM user smarter with each use
keyanzhang · x · 2026-11-09
A shared note titled 'A perfect human' sketches the ideal LLM user: high clarity of thinking, precisely declaring intent, high-level goals and definition of done, refining what they want to want, knowing the map is not the territory, updating priors constantly, and expanding decision trees with creativity while pruning them via principles. It ends with two questions: how do we make every LLM user a perfect human, and how do we build agents that make us smarter each time we use them?
More from AGI Musings
- Designer warns AI tools strip out struggle needed to build judgment, calls for slower tools — jakubzeg · 2026-11-09
- Free 1-hour AI lecture: 95% of people still use AI like a calculator — LinusEkenstam · 2026-11-09
- US business services added 70,000 jobs in October despite AI exposure fears — kimmonismus · 2026-11-09
- AI timelines debates go nowhere because everyone secretly defines superintelligence differently — sebkrier · 2026-11-09
- Not Every Problem Needs Agentic AI: Teams Pay 10-30x More for the Wrong Choice — DavidLinthicum · 2026-11-09
- Cambridge's David Krueger on MIRI: the problems are hard — what matters is the capabilities-to-safety research ratio — DavidSKrueger · 2026-11-09