Msg Len
I’ll be brief, omit needless words.
Intelligence is prediction is compression because
Compression is finding a code that makes the data shorter
And codeword lengths are probabilities
So codes are probability distributions
But probability distributions are prediction strategies.
- Feature Selection by (1 Nov 2021 0:22 UTC; 320 points)
- Message Length by (20 Oct 2020 5:52 UTC; 134 points)
- Unnatural Categories Are Optimized for Deception by (8 Jan 2021 20:54 UTC; 89 points)
- A gentle primer on caring, including in strange senses, with applications by (30 Aug 2022 8:05 UTC; 10 points)
And prediction strategies are almost optimization procedures?
Did your really need to say that you’d be brief? Wasn’t it enough to say that you’d omit needless words? :)
But then he’d lose the Strunk and White allusion.
I approve the haikuesque format.
Do you agree that the “bijection” Intelligence → Prediction preserves more structure than Prediction → Compression?