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 (Nov 1, 2021, 12:22 AM; 320 points)
- Message Length by (Oct 20, 2020, 5:52 AM; 134 points)
- Unnatural Categories Are Optimized for Deception by (Jan 8, 2021, 8:54 PM; 89 points)
- A gentle primer on caring, including in strange senses, with applications by (Aug 30, 2022, 8:05 AM; 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?