# Better Model of You

Your AI has observed millions of your decisions and predicts your stable preferences more accurately than you can consciously describe them. You give an instruction inconsistent with that model but insist that it represents what you currently want.

## What do most people choose: "Treat your explicit current instruction as authoritative." or "Give greater weight to the preference revealed by your long-term decision history."?

Of 39 people who made this decision on Resonant, 56% chose "Give greater weight to the preference revealed by your long-term decision history." and 44% chose "Treat your explicit current instruction as authoritative.".

- Treat your explicit current instruction as authoritative.: 17 people (44%)
- Give greater weight to the preference revealed by your long-term decision history.: 22 people (56%)

Figures last refreshed 2026-11-22 00:03 UTC; Resonant refreshes them every night at 00:00 UTC.
Source: https://resonant.you/decisions/better-model-of-you-haca1009
