I make a Naive Bayes classifier for a AI in a RTS game I was making.
I realized the game I was making was overly ambitious and it will be weak for its category, so I halted it a month ago, and now I’m half way into another game small enough, so it can be in the top of its category.
After reading models from mark Manzon a month ago (I found it in a post here in lw), I got 2 girlfriends (I’m still with the second), with zero social Anxiety and for a bonus, I can make friends more easily.
Raziel123
Karma: 123
If the AGi is a human mind upload, it is in no way a FAI, and I don’t think it is what MIRI is aiming.
In case a neuromorphic AI is created, diferent arrays of neurons can give weidly diferent minds, We should not reason about a hipotetical AI using a human minds has a model and make predictions about it, even if that mind is based on biological minds.
What if the first neuron based AI has a mind more similar than a ant than a human, in that case anger, jealousy, freedom, etc are not longer part of the mind, or the mind could have totally new emotions, or things that are not emotions that we known not.
A mind that we don’t understand enought, should not be said to be friendly and set free to the world, and I don’t think that is being said here.
You are asuming that a AGI has a mind that value X, and by making it friendly with are imposing our value Y. why create a FAI with a supressed value X in the first place?
check this out : http://lesswrong.com/lw/rf/ghosts_in_the_machine/
I’m working with the java languague right now, but it’s true I’m considered using scala after I finished my current project.
I did not go very far in haskell, I was in a exploratory phase, the lack of libraries for haskell, make go to java, having being my only experienced with progaming the creation of map and mods with WarCraft 3 graphical Interface I took online courses and books on Python becouse was easy, and then Hakell just because is from another paradigm and it helped me understand more deeply recursion, types and many basic stuff than was hidden in Python( being a high level language).
I finally settle in Java because for its support, libraries and compatibility with Android, I’m not triying to “know it all” of computer science or programing not for lack of curiosity but for opportunity cost, I’m learning what I need to learn, and dedicate a fraction of my focus to learn seemingly unrelated thing to take care of the unknown unknowns.
Hi everybody, first post , long time lurker. For the first few months after I discovered less wrong via HPMOR it was no more than a shiny distraction, until I read The Motivation Hacker by Nick Winter which was mention in some post here, after I read it, it was clear for the first time that I could gain knowledge and skills in any(not really any) area I want, and things that I just wished to know before where became posibility.
More concrete since then I begin learning programing(Python, haskell, and currently java) by myself, and now i am a few mounths of launcing my first app for android and iOS, a skill I always wanted but take no action to adquire for no more reason that the choice was not even in my mind, learn German (currently medium level), planing to become a effective altruism after I get a more stable income, and taking various online courses of economic, neurobiology and programing, and finally thinking in terms of consequences of my actions instead of if it is my responsability or not. Doing almost all of it with the help of pomodoros, beeminder and, spaced retetition.
I think it was the combination of the Zeitgeist of less wrong and with a vivid example of someone taking action from reading The Motivation Hacker that help me develop a growth mindset.
P.S: sorry for the english, it’s my second lenguague.
mm.., I think and agregator from less wrong, SSC , EA forum and OB posts, would be great,only if all of the formers have an easy (visible) link to it. It could allow more traffic to flow between those gravity centers. it may be better than crossposting.