This sequence predictor can potentially be really useful (for example, predict future
siai publications from past siai publications then proceed to read the article which
give a complete account of Friendliness theory...) and is not dangerous in itself.
I see a way in which a simple, super-intelligent sequence predictor can be dangerous. If it can predict an entire journal issue, it surely can simulate a human being sufficiently well to build a persuasive enough argument for letting it out of the box.
However you don’t need a complicated program predictor, you can just use the speed prior instead of the universal prior.
I see a way in which a simple, super-intelligent sequence predictor can be dangerous. If it can predict an entire journal issue, it surely can simulate a human being sufficiently well to build a persuasive enough argument for letting it out of the box.
However you don’t need a complicated program predictor, you can just use the speed prior instead of the universal prior.