LLM: A mind of a toddler who has also read every book in the world.
It's confusing to us, we don't have any points of reference for it.
We get tricked by an erroneous mental model of what it can and cannot do.
From other episodes
- The best UXR comes up with a mental model and then design studies to falsify it.2026-04-06
- Users are stickier to UX than agents are to APIs.2026-03-23
- The ability and willingness to absorb disconfirming evidence is a superpower.2026-03-17
- Leave easter eggs for delight in your product.2026-03-09
- Excellent analysis by Orion Reed on Digital Topology and Economic Power.2026-03-02
- I wonder if the whole focus on AGI is downstream of LLMs talking like humans.2026-03-02
- The technical term for when a tool merges with our mental model is mechanical sympathy.2026-02-23
- A rough mental model of Reinforcement Learning curriculum.2026-02-16