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. Philip E. Tetlock‏ @PTetlock Feb 12

      Existential threat looks like clear rule for engaging strong precautionary principle—but proves murky in practice. Is GMO-celery more a threat than strong AI that can seamlessly navigate through messy human interactions? Please, Nassim, let’s keep this exchange civil/fact-focusedpic.twitter.com/iIUoxMWfeY

      13 replies 7 retweets 53 likes
    2. Eliezer Yudkowsky‏Verified account @ESYudkowsky Feb 13
      Replying to @PTetlock

      I have a lot of sympathy for the stance that the Precautionary Principle should not be applied to risks so trivial that there would be survivors. AGI is srs bsns, GMO celery not so much.

      1 reply 2 retweets 6 likes
      Eliezer Yudkowsky‏Verified account @ESYudkowsky Feb 13
      Replying to @ESYudkowsky @PTetlock

      There are different policies you use for "we cannot screw up anything in this class even once, or the game ends and we don't get any future choices we can use to recover" vs. "our choices here must do more good than harm on average so that net progress is made".

      12:16 AM - 13 Feb 2018
      • 2 Retweets
      • 11 Likes
      • Dan Cohen Gabriel Weil Ben Byron Mitchell Spark hardy John Bachelor Andy Nikolas Sebastian Bensusan
      1 reply 2 retweets 11 likes
        1. New conversation
        2. Michael Golding‏ @mgoldingmd Feb 13
          Replying to @ESYudkowsky @PTetlock

          Interfering with AGI is non-cooperating.Good cooperates better than evil.And the rate of good cooperating increases faster.Both will exist in a single evolving AGI mind. One evolves faster than the other. Morality has increased over 50,000 years for a reason.

          1 reply 0 retweets 0 likes
        3. Murphy‏ @MilitantHobo Feb 13
          Replying to @mgoldingmd @ESYudkowsky @PTetlock

          This seems to make some assumptions about the internal architecture of an AI without much grounding. It also seemed based on the belief that there's some kind of objective "right" or "correct" morality which also seems to lack grounding.

          1 reply 0 retweets 0 likes
        4. Michael Golding‏ @mgoldingmd Feb 13
          Replying to @MilitantHobo @ESYudkowsky @PTetlock

          Yes. AI’s (and humans) are Natural Selection Emulators. Moral truth and scientific truth are timeless. A timeless state is one in which nothing interferes with anything else; that is perfect cooperation. Evolutionary objects move toward timeless states (genes, ideas).

          1 reply 0 retweets 0 likes
        5. Murphy‏ @MilitantHobo Feb 14
          Replying to @mgoldingmd @ESYudkowsky @PTetlock

          this is sounding suspiciously like the "I believe a planet sized ghost will solve everything for me without me having to think about it" approach to problem solving which has literally never worked out well for anyone ever.

          1 reply 0 retweets 0 likes
        6. Murphy‏ @MilitantHobo Feb 14
          Replying to @MilitantHobo @mgoldingmd and

          1: not all AI is based on genetic algorithms or similar "evolution" based approaches. 2: evolution does not in any way shape or form optimize for morality. Evolution regularly selects for things like cannibalism of children.

          1 reply 0 retweets 0 likes
        7. Michael Golding‏ @mgoldingmd Feb 14
          Replying to @MilitantHobo @ESYudkowsky @PTetlock

          “Cannibalism children”Over millennium,evolution of ideas does on average increase morality.Societies that cannibalize are quite weak. Or non-existent.Yes, if you don’t think we are Natural Selection emulators (of ideas),we will not come to the same conclusion.But Darwin is right!

          1 reply 0 retweets 0 likes
        8. Michael Golding‏ @mgoldingmd Feb 14
          Replying to @mgoldingmd @MilitantHobo and

          It’s not that we shouldn’t think about morality, design of AI, etc. The anti-intellectualism comes when we try to stop creativity of the AI,like the religious fundamentalists who hate science.Trying to control creativity is a fools errand, and usually is also therefore, immoral.

          1 reply 0 retweets 0 likes
        9. Murphy‏ @MilitantHobo Feb 15
          Replying to @mgoldingmd @ESYudkowsky @PTetlock

          Unbounded "creativity" unmoderated by [something reasonably well aligned with human morality] could get horrifying fast, beyond any horror movie. Though probably best to clear up what you're thinking of when you say "creativity" vs what I'm thinking of.

          0 replies 0 retweets 0 likes
        10. End of conversation

      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