Idea Ripper // ArchiveCards: 1555 [Live] | Updated: 2026-10-14
Card #c726IR // #c726Synthesis

one should not focus on the errors of the predictor, but on its improvements.

— In our words · Source: Driven by Compression Progress (Jürgen Schmidhuber)

[Use when]

Use when building any learning system, or judging your own attention: measure progress, not confusion.

[Why it matters]

The 1991 fix to the 1990 curiosity model: rewarding raw prediction error sends the agent to stare at noise forever, because noise always gives high error. Reward the derivative — the improvement — and the agent hunts learnable regularity instead.

More from Driven by Compression Progress

#c718This drive maximizes interestingness, the first derivative of subjective beauty or compressibility, that is, the steepness of the learning…Use when judging whether something is boring: ask whether the data went flat, or whether your learning curve… #c719I argue that data becomes temporarily interesting by itself to some self-improving, but computationally limited, subjective observer once…Use when the same thing bores you now that electrified you a year ago: you compressed it, and the derivative… #c720Curiosity is the desire to create or discover more non-random, nonarbitrary, regular data that is novel and surprising not in the…Use when designing anything meant to hold attention: the target is learnable regularity, not noise.