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.

    Eliezer Yudkowsky‏Verified account @ESYudkowsky 4 Jan 2017

    Let us term an AGI 'safe' if it has a less than 50% probability of causing more than 1 billion human deaths

    3:24 AM - 4 Jan 2017
    • 6 Retweets
    • 23 Likes
    • Buck Shlegeris lot Connor Flexman Jake Witmer MugaSofer Trippy Salmon David McDougall Brienne Yudkowsky Dimitrios Kokkinos
    11 replies 6 retweets 23 likes
      1. New conversation
      2. Vitalik Non-giver of Ether‏Verified account @VitalikButerin 22 Jan 2017
        Replying to @ESYudkowsky

        Edge instantiation failure: what if it just permanently freezes everyone in carbonite?

        1 reply 1 retweet 5 likes
      3. Eliezer Yudkowsky‏Verified account @ESYudkowsky 22 Jan 2017
        Replying to @VitalikButerin

        This is from our perspective, not a try at an explicit utility function.

        0 replies 0 retweets 0 likes
      4. End of conversation
      1. New conversation
      2. Jon Mellon‏ @jon_mellon 4 Jan 2017
        Replying to @ESYudkowsky

        what if an AGI:90% chance of not working 9% chance of bad outcome and 1% chance of good outcome. Is it safe? What if I make 500

        1 reply 0 retweets 0 likes
      3. Eliezer Yudkowsky‏Verified account @ESYudkowsky 4 Jan 2017
        Replying to @jon_mellon

        Let us not term a computation an "AGI" if it doesn't work.

        1 reply 0 retweets 5 likes
      4. Jon Mellon‏ @jon_mellon 4 Jan 2017
        Replying to @ESYudkowsky

        how is work defined in this context?

        0 replies 0 retweets 0 likes
      5. End of conversation
      1. New conversation
      2. Franciszek Żak‏ @maniexx 4 Jan 2017
        Replying to @ESYudkowsky

        Note to self: do not use anything declared safe by @ESYudkowsky

        1 reply 2 retweets 3 likes
      3. Ilzolende Ianthe‏ @ilzolende 4 Jan 2017
        Replying to @maniexx @ESYudkowsky

        note to self: independently verify the safety of things yudkowsky considers safe

        0 replies 0 retweets 3 likes
      4. End of conversation
      1. Walter Langendorf‏ @Wlungr 4 Jan 2017
        Replying to @ESYudkowsky

        that seems like a controversial measurement.

        0 replies 0 retweets 1 like
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Jake Witmer‏ @Jake_Witmer 26 Jan 2017
        Replying to @ESYudkowsky

        "...Good enough for government work."

        0 replies 0 retweets 0 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Alex Andronikou‏ @lex_andronikou 5 Jan 2017
        Replying to @ESYudkowsky

        My top 3 analytical kings are Marcel Proust, Eliezer Yudkowsky and Sam Harris. Who are yours Eliezer?

        0 replies 0 retweets 0 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Daniel Boese‏ @DataPacRat 5 Jan 2017
        Replying to @ESYudkowsky

        Do you consider em-style uploaded brains as 'safe' or 'unsafe' for these purposes?

        0 replies 0 retweets 0 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. Faun of Foggy Hollow‏ @makoConstruct 4 Jan 2017
        Replying to @ESYudkowsky

        I know you're joking but out of curiosity is there a robust way to distinguish chaos theory causation from direct action?

        1 reply 0 retweets 0 likes
      3. Faun of Foggy Hollow‏ @makoConstruct 4 Jan 2017
        Replying to @makoConstruct @ESYudkowsky

        Like if it influences a bomb maker, causing the shrapnel of a bomb to kill people it otherwise wouldn't have (sparing others)

        1 reply 0 retweets 0 likes
      4. Faun of Foggy Hollow‏ @makoConstruct 4 Jan 2017
        Replying to @makoConstruct @ESYudkowsky

        Is that causing deaths?

        0 replies 0 retweets 0 likes
      5. End of conversation
      1. ישוע השטן‏ @EamDominus 4 Jan 2017
        Replying to @ESYudkowsky

        99% chance of killing 250,000 ppl... safe?

        0 replies 0 retweets 0 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Jeff Lonsdale‏ @JeffLonsdale 4 Jan 2017
        Replying to @ESYudkowsky

        Shouldn't they be measured by some expected value calculation? So expected deaths less than 500M?

        0 replies 0 retweets 0 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Joe Cooper‏ @swelljoe 4 Jan 2017
        Replying to @ESYudkowsky

        but what if I really want my phone to make good restaurant recommendations? Isn't it worth the minor tradeoffs?

        0 replies 0 retweets 0 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo

    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