Wiki Contributions

Comments

With my current research together with John Vervaeke and Johannes Jaeger, I'm continuing the work on the cognitive science of rationality under uncertainty, bringing together the axiomatic approach (on which Stanovich et al. build) and the ecological approach. 

Here I talk about Rationality and Cognitive Science on the ClearerThinking Podcast. Here is a YouTube conversation between me and John, explaining our work and the "paradigm shift in rationality". Here is the preprint of the same argumentation as "Rationality and Relevance Realization". John also mentions our research multiple times on the Jim Rutt Show.

I've always admired your writings on the topic and you were one of the voices that led me to my current path, thank you so much, Luke.

As always: For further information join or look into the Facebook group "Rationality Vienna" - here is also the FB-event: https://www.facebook.com/events/779237562115156/

Here is the link for the FB-event - for any further information:

https://www.facebook.com/events/1491377887814691

(Might be that you first need to become member or "Rationality Vienna" to see it)

Me - and many others from the meetup in Vienna - already signed up. This - probably - will be super awesome. Looking forward to it!

Review about the Rationality Meetup in Vienna on 27.09.2014

Superintelligence Summary by Marko Thiel

People who were there: Andreas, Matthias Brandner, Manuel K., Monika, Marko, Viliam Bur, Alex, Philip, Anna, Philipp, Tino/Sandy, Austin, Milica, Luka, Ivan, Axel, Lea, Lio, Andreas V., Manuel M. (20 people - awesome! And so many were new!)

Superintelligence by Nick Bostrom (presented by Marko Thiel)

First announcement: ethics will not be discussed and rather be ignored today, because otherwise he would never finish

Quote "Let an ultraintelligent machine be defined as a machine that can far surpass all the intellectual activities of any man however clever. Since the design of machines is one of these intellectual activities, an ultraintelligent machine could design even better machines; there would then unquestionably be an “intelligence explosion,” and the intelligence of man would be left far behind. Thus the first ultraintelligent machine is the last invention that man need ever make, provided that the machine is docile enough to tell us how to keep it under control."

definition:

(I sadly didn't take notes here)

paths:

  • AI -> strong AI

  • whole brain emulation

  • biological cognition (improve humans, chemical substances/nootropics, embryo selection -> lots of generations in vitro)

  • interface with machine

  • networks and organizations

forms:

  • speed Superintellicence (like human but faster)

  • collective Superintelligence (together smarter)

  • quality Superintelligence (totally different to human)

intelligence explosion:

  • there will be a crossover after which the machine itself will go on improving the system

  • graph to show how similar an idiot and Einstein are compared to a mouse or Superintelligence

rate of intelligence change

AI takeover:

  1. precritial

  2. intelligence amplification

  3. cover + preparation

  4. overt implementation

-> arises the question of where the motivation to do so comes from!

the super intelligence will:

  • the orthogonality thesis: any intelligence can build a pair with any motivation (Eliezer would probably call it "anti prediction)

Castes:

  • oracles

  • genies

  • sovereign

  • tool

predictability:

  • design

  • convergent instrumental goals (for example: self-preservation, goal-content integrity, cognitive enhancement, technology, resource acquisition -> infrastructure profusion)

other topics: failure modes, control problem, acquire values, choosing who to choose, do what I mean, the strategic picture

Comments I wrote down

by Andreas: "Does SI include self-awareness?" answer: "No"

by Ivan: Has someone tried to breed an human intelligent dog?

by Lio: Is it possible to have something that's good in all the things? -> Viliam: Yes, with a network structure

by Austin: Is there a difference between biological or programmed happiness? -> Manuel: the utility function of a thermostat is to be at 20 degrees, it doesn't WANT to be there

in the evening:

  • We talked about daily things members of the group do which they consider rational/daily effective rituals/personal sleeping duration

for the next meetup:

  • We will vote on the date in the Facebook group

  • we will have three topics and the third one will be to collect personal goals we want to achieve with/in the group/ideas we have for the group

However, I filled in the application with the information about my personal location, so that he/they can see, that there is need for such events in Europe, too :) (maybe you should do that, too!)

Maybe he can give his plans for this event to some of us and we can organize our own event as a subunit.

Since I will not be able to attend "the rational ritual retreat" I will just post my thoughts on this topic here :) I already talked about this with some of the people from LessWrong Vienna, but I will write it down for the whole community, too:

What do you think about "rational alternatives" to important conventional events (but of course not exactly on the official dates - because people probably meet their families then) or creating "rational annual events"? I personally don't experience big meaning in official celebrations, but I actually enjoy celebrations, even more with smart people who in general share my interests :) Also all the official celebrations probably had an important purpose in the wheel of the year - for me they all lost their purpose over time (because not believing in it or not taking part in it) so at least the rational alternatives should deliver it.

Some vague ideas I had:

  • rational alternative to christmas: We could have a talk or invite someone to speak about effective altruism (I personally associate christmas with "giving") and then reflect about which projects we would love to support monetarily and collect money or something like that (maybe someone of you has better ideas?)

  • rational alternative to New Year's Eve/Day (doesn't have to be exactly on this day) : coming together, celebrating the old/new year with good food (maybe cooking together or something like that) or whatever you like - but instead of just mention some new year's resolutions making it a huge part of the evening/day -> exercises for reflection about the last year and wishes/plans for the next (+ use Alex Vermeer's guide), defining new goals, sharing background knowledge about goal setting and motivation, publicly announcing goals for social control/pressure (I would offer to have some talks about the topics)

  • rational alternative to the fasting period: I think fasting is not a stupid idea - there is also research that shows that reducing the daily intake correlates with a longer life in general (yeah, I know, correlation...) and I experienced that eating far less can really help to "free your mind". However: Also to just reflect about our diet, have some healthy cooking events together, trying soylent collectively or something like that would be an option. Or to do a lot of sport!

  • rational alternative to Easter: since it's officially about "Jesus who overcame death" we could make a event about longevity and immortality and share scientific research on the topics

  • summer/winter solstice: someone who is into this topics could teach the rest more about astronomy/astro physics

Of course I'm aware that there is no need to have any connection/correlation to official christian celebrations (and that some even might think it's contraindicated) - we can of course invent our own things independently (designed for a special purpose)

Load More