Skip to content
  • Home Home Home, current page.
  • Moments Moments Moments, current page.

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @
  • Language: English
    • Bahasa Indonesia
    • Bahasa Melayu
    • Català
    • Čeština
    • Dansk
    • Deutsch
    • English UK
    • Español
    • Filipino
    • Français
    • Hrvatski
    • Italiano
    • Magyar
    • Nederlands
    • Norsk
    • Polski
    • Português
    • Română
    • Slovenčina
    • Suomi
    • Svenska
    • Tiếng Việt
    • Türkçe
    • Ελληνικά
    • Български език
    • Русский
    • Српски
    • Українська мова
    • עִבְרִית
    • العربية
    • فارسی
    • मराठी
    • हिन्दी
    • বাংলা
    • ગુજરાતી
    • தமிழ்
    • ಕನ್ನಡ
    • ภาษาไทย
    • 한국어
    • 日本語
    • 简体中文
    • 繁體中文
  • Have an account? Log in
    Have an account?
    · Forgot password?

    New to Twitter?
    Sign up
ESYudkowsky's profile
Eliezer Yudkowsky
Eliezer Yudkowsky
Eliezer Yudkowsky
Verified account
@ESYudkowsky

Tweets

Eliezer YudkowskyVerified account

@ESYudkowsky

Ours is the era of inadequate AI alignment theory. Any other facts about this era are relatively unimportant, but sometimes I tweet about them anyway.

Joined June 2014

Tweets

  • © 2018 Twitter
  • About
  • Help Center
  • Terms
  • Privacy policy
  • Cookies
  • Ads info
Dismiss
Previous
Next

Go to a person's profile

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @

Promote this Tweet

Block

  • Tweet with a location

    You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more

    Your lists

    Create a new list


    Under 100 characters, optional

    Privacy

    Copy link to Tweet

    Embed this Tweet

    Embed this Video

    Add this Tweet to your website by copying the code below. Learn more

    Add this video to your website by copying the code below. Learn more

    Hmm, there was a problem reaching the server.

    By embedding Twitter content in your website or app, you are agreeing to the Twitter Developer Agreement and Developer Policy.

    Preview

    Why you're seeing this ad

    Log in to Twitter

    · Forgot password?
    Don't have an account? Sign up »

    Sign up for Twitter

    Not on Twitter? Sign up, tune into the things you care about, and get updates as they happen.

    Sign up
    Have an account? Log in »

    Two-way (sending and receiving) short codes:

    Country Code For customers of
    United States 40404 (any)
    Canada 21212 (any)
    United Kingdom 86444 Vodafone, Orange, 3, O2
    Brazil 40404 Nextel, TIM
    Haiti 40404 Digicel, Voila
    Ireland 51210 Vodafone, O2
    India 53000 Bharti Airtel, Videocon, Reliance
    Indonesia 89887 AXIS, 3, Telkomsel, Indosat, XL Axiata
    Italy 4880804 Wind
    3424486444 Vodafone
    » See SMS short codes for other countries

    Confirmation

     

    Welcome home!

    This timeline is where you’ll spend most of your time, getting instant updates about what matters to you.

    Tweets not working for you?

    Hover over the profile pic and click the Following button to unfollow any account.

    Say a lot with a little

    When you see a Tweet you love, tap the heart — it lets the person who wrote it know you shared the love.

    Spread the word

    The fastest way to share someone else’s Tweet with your followers is with a Retweet. Tap the icon to send it instantly.

    Join the conversation

    Add your thoughts about any Tweet with a Reply. Find a topic you’re passionate about, and jump right in.

    Learn the latest

    Get instant insight into what people are talking about now.

    Get more of what you love

    Follow more accounts to get instant updates about topics you care about.

    Find what's happening

    See the latest conversations about any topic instantly.

    Never miss a Moment

    Catch up instantly on the best stories happening as they unfold.

    1. David Chapman‏ @Meaningness May 28
      Replying to @ArtirKel @ESYudkowsky @juliagalef

      Oh! After brushing my teeth and before I forget :) maybe this is helpful: When designing an airplane wing, use finite element analysis, not DT. Implementing a network protocol, use a parser, not DT. In hydrology, use percolation theory, not DT.

      2 replies 0 retweets 0 likes
    2. David Chapman‏ @Meaningness May 28
      Replying to @Meaningness @ArtirKel and

      I don’t think any of these are “approximations of DT” in any interesting sense. If you declare by fiat that DT is the Theory of Everything, then you could try to force-fit it… but that’s going to come out awkward and unconvincing.

      1 reply 0 retweets 0 likes
    3. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 28
      Replying to @Meaningness @ArtirKel @juliagalef

      If you don't see DT's laws as governing these cases, or if you think it's a critique of the use of DT that some option space is too large to be practically approximated; then I have the sense of pointing to a thing and a use that's still not in your ontology.

      1 reply 0 retweets 1 like
    4. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 28
      Replying to @ESYudkowsky @Meaningness and

      This is like saying "When building a car engine, use the Handbook of Chemistry and Physics, thermodynamics may not tell you the tensile strength of steel". It's a type error. Like thermodynamics, DT holds true everywhere, whether or not it's useful to think about it right now.

      1 reply 0 retweets 2 likes
    5. David Chapman‏ @Meaningness May 29
      Replying to @ESYudkowsky @ArtirKel @juliagalef

      So I think what you said here does express the crux of our disagreement (as I suggested earlier in the conversation). It seems that you think (1) DT has a special status among mathematical systems, and (2) that it is actually *true* of the macroscopic physical world.

      1 reply 0 retweets 1 like
    6. David Chapman‏ @Meaningness May 29
      Replying to @Meaningness @ESYudkowsky and

      If we wanted to continue the discussion, and if you agree, we could see (1) in what way DT is special, and (2) in what way it is “true everywhere.”

      1 reply 0 retweets 1 like
    7. David Chapman‏ @Meaningness May 29
      Replying to @Meaningness @ESYudkowsky and

      Thermodynamics is physics, not just math, and it is (presumably) true everywhere in space, by virtue of accurately representing physical phenomena. The Chomsky Hierarchy, relating parsers & language types, is “true everywhere” in the sense that physical space is irrelevant to it

      1 reply 0 retweets 1 like
    8. David Chapman‏ @Meaningness May 29
      Replying to @Meaningness @ESYudkowsky and

      I take it that by “DT is true everywhere” you mean it is the correct analysis of all physical events (of a certain type, maybe), rather than just that it is a consistent branch of math. I don’t think that’s true.

      2 replies 0 retweets 1 like
    9. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
      Replying to @Meaningness @ArtirKel @juliagalef

      "The correct analysis of all physical events" - I don't even understand what you think I mean, or what or what this could possibly mean, unless you believe that I believe something incoherent rather than wrong. It's like saying that a fish is a correct analysis of all events.

      1 reply 0 retweets 1 like
    10. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
      Replying to @ESYudkowsky @Meaningness and

      Once you inject preference and uncertainty into a perspective on an event, however fuzzily, DT validly describes certain laws governing performance, like coherence theorems. If and only if your choices cannot be viewed as coherent, the strategy is dominated, etcetera.

      1 reply 0 retweets 0 likes
      Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
      Replying to @ESYudkowsky @Meaningness and

      Thermodynamics has a similar property, as it happens; entropy at its core is defined relative to uncertainty. If you understand all the motions in a classical system, you can extract it as free energy rather than leaving it as heat.

      10:55 AM - 29 May 2018
      1 reply 0 retweets 0 likes
        1. New conversation
        2. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
          Replying to @ESYudkowsky @Meaningness and

          Aren't probabilities such terribly fuzzy things? Where oh where do the priors come from? And yet, this doesn't really make very much difference to a glass of hot water, and by being more careful we can phrase thermodynamics in a less subjective way.

          1 reply 0 retweets 0 likes
        3. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
          Replying to @ESYudkowsky @Meaningness and

          So thermodynamics, at its core, has a certain twist of subjectivity; it is relative to things an observer knows. But the fuzzy parts of the subjectivity factor out cleanly in almost all practice, and the tiniest injection of perspective suffices to animate the mathematical core.

          1 reply 0 retweets 2 likes
        4. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
          Replying to @ESYudkowsky @Meaningness and

          DT requires a larger injection of perspective; preference as well as probability. Like thermodynamics, you can inject this subjectivity in the wrong place and imagine that nobody comprehends the motions in a spinning cylinder and that the rotation is all waste heat.

          2 replies 0 retweets 1 like
        5. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
          Replying to @ESYudkowsky @Meaningness and

          But once you go so far as to map certain parts of the system onto preference and belief, the coherence theorems hold like the theorems they are. In that sense they're more universal, and less physically informative, than thermodynamics.

          1 reply 0 retweets 0 likes
        6. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
          Replying to @ESYudkowsky @Meaningness and

          Most mappings on the system will be useless. If you regard a particular molecule as having compact preferences and beliefs, it will probably do very poorly. Human beings do have relatively compact preferences and beliefs, on the other hand, and applying it to humans make sense.

          1 reply 0 retweets 0 likes
        7. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
          Replying to @ESYudkowsky @Meaningness and

          This is not because humans obey the prescriptions of decision theory. It is because humans are making things that can be viewed as decisions. This is not because human beliefs are coherent. It's because humans can be well-viewed as believing things even if incoherently.

          1 reply 0 retweets 1 like
        8. Eliezer Yudkowsky‏Verified account @ESYudkowsky May 29
          Replying to @ESYudkowsky @Meaningness and

          It seems to me that you don't understand the very abstract use that is being made of decision theory. It's not a recipe or an algorithm. It's a generalization relating coherent or incoherent behavior to performance, making far more minimal assumptions than you seem to think.

          1 reply 0 retweets 0 likes
        9. David Chapman‏ @Meaningness May 29
          Replying to @ESYudkowsky @ArtirKel @juliagalef

          Well… I *think* I understand this; but I may be wrong! We clearly have very different cognitive styles, which makes it difficult for us to understand each other.

          3 replies 0 retweets 1 like
        10. 8 more replies

      Loading seems to be taking a while.

      Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

        Promoted Tweet

        false

        • © 2018 Twitter
        • About
        • Help Center
        • Terms
        • Privacy policy
        • Cookies
        • Ads info