126K views · Feb 26, 2020 · 1:39:56 · 1 HN recommender · 3 mentions · discussed 2020–2025
Lex Fridman interviews Marcus Hutter of DeepMind about universal artificial intelligence, AIXI, Kolmogorov complexity, Solomonoff induction and the idea of intelligence as compression.
Why Hacker News points people here: Referenced as an accessible explanation of Kolmogorov complexity and Hutter's view of intelligence as compression.
“it made sense to me”HN comment, 2020
“it made sense to me”
Hutter explains Kolmogorov complexity in understandable terms.
New concepts to me coming from outside the field. Kolmogorov complexity was discussed just recently on Lex Fridman's podcast with Marcus Hutter - this video I don't know enough to say how accurate Hutter's explanation is but it made sense to me.
“Then there is the interview with Hutter himself”
Interview with Hutter on intelligence as compression.
> Are they? They are actually. It's a kind of revelation when you realise this statement is true. There are people in AI who have thought long about the problem of intelligence and had this realisation. For example: link Then there is the interview with Hutter himself: this video You can even semi-formally derive this from Bayes' rule. Let's consider intelligence to be the ability to predict future data from past data. This requires building a model for the past data that can make predictions. So intelligence produces the most likely model M given data D: argmax_M P(M|D) which from Bayes' rule is: argmax_M P(M|D) = P(D|M)*P(M)/P(D) You convert probabilities to information by taking the negative log: argmin_M -log(P(M|D)) = -log(P(D|M)) + -log(P(M)) We lost -log(P(D)) because we consider D constant so it can't influence the minimum. You can read the above informally as: The most likely model (the most general model) that can make predictions from data D is that where the (encoding of the model with the least information) plus (the encoding of the data using the model) is minimal. This is essentially a statement about compression. I'm sure an AI person could do this better. This is also known as: link or in philosophy as: link
Hutter discusses intelligence and compression.
I was thinking about this lex friedman podcast with Marcus Hutter. Also, Joshua Bach defined intelligence as the ability to accurately model reality.. is lossless compression itself intelligence or a best fit model- is there a difference? this video
