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
paulg's profile
Paul Graham
Paul Graham
Paul Graham
Verified account
@paulg

Tweets

Paul GrahamVerified account

@paulg

paulgraham.com
Joined August 2010

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.

    Paul Graham‏Verified account @paulg 3 Jul 2017

    Idea: Divide old news stories into ones that mattered and didn't, and then use that to train a filter to use on current stories.

    8:43 AM - 3 Jul 2017
    • 220 Retweets
    • 950 Likes
    • W. Kevin McClellan atty eleti Max Aaron McClendon tysonmaly Joanna Pedrina Harry Dry William Channing Allen
    50 replies 220 retweets 950 likes
      1. New conversation
      2. Paul Graham‏Verified account @paulg 3 Jul 2017
        Replying to @paulg

        It would be fascinating to see which words had most predictive value in each direction.

        14 replies 6 retweets 85 likes
      3. Peter MacRobert‏ @PeteM 3 Jul 2017
        Replying to @paulg

        Definition of "Mattered" is the definition of classifier bias.

        0 replies 1 retweet 13 likes
      4. End of conversation
      1. New conversation
      2. Mats Stafseng Einarsen‏ @matseinarsen 3 Jul 2017
        Replying to @paulg @impcapital

        The more I think about metrics for what matters the more it feels like very little news matter.

        3 replies 0 retweets 8 likes
      3. Sarah Cone‏ @impcapital 3 Jul 2017
        Replying to @matseinarsen @paulg

        Facts that cause you to see reality in a different way are the most useful news to me; also hearing about new things.

        0 replies 0 retweets 4 likes
      4. End of conversation
      1. Anne Weiler‏ @annewellpepper 3 Jul 2017
        Replying to @paulg

        Matter to whom?

        0 replies 1 retweet 6 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. Ilya Sukhar‏ @ilyasu 3 Jul 2017
        Replying to @paulg

        What definition of "mattered" did you have in mind?

        2 replies 0 retweets 7 likes
      3. Ryan Moulton  🌎 🌍 🌏 🌡 📈‏ @moultano 3 Jul 2017
        Replying to @ilyasu @paulg

        Traffic starting a year after publication.

        1 reply 0 retweets 1 like
      4. 1 more reply
      1. New conversation
      2. Alex Kern‏ @kernio 3 Jul 2017
        Replying to @paulg

        Is this not the premise of a filter bubble?

        1 reply 0 retweets 3 likes
      3. Sean Linehan‏ @_slinehan 3 Jul 2017
        Replying to @kernio @KernCanCode @paulg

        Yeah except the filter is "stories that are important" vs. "stories that make you click"

        1 reply 0 retweets 0 likes
      4. Alex Kern‏ @kernio 3 Jul 2017
        Replying to @_slinehan @paulg

        So the feedback is explicit ("This article matters") as opposed to implicit ("This article's title is interesting"). Same concept holds.

        1 reply 0 retweets 1 like
      5. Sean Linehan‏ @_slinehan 3 Jul 2017
        Replying to @kernio @KernCanCode @paulg

        Identical. Just different loss function

        0 replies 0 retweets 1 like
      6. End of conversation
      1. Jeremy Mims‏ @jeremymims 3 Jul 2017
        Replying to @paulg

        I think we'd find that most "breaking" news turned out not to matter.

        0 replies 0 retweets 3 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. Kristin Eberth‏ @kristineberth 3 Jul 2017
        Replying to @paulg

        Our feed at @PressReader learns which stories ppl read most deeply & shows those to similar readers.

        1 reply 0 retweets 1 like
      3. Kristin Eberth‏ @kristineberth 3 Jul 2017
        Replying to @kristineberth @paulg @PressReader

        It surfaces v different (hi-qual) content. Not obfuscated by likes/shares & our bias toward sharing click bait or headlines we agree with.

        0 replies 0 retweets 1 like
      4. End of conversation
      1. Anton Borysov‏ @antonbrsv 3 Jul 2017
        Replying to @paulg

        Isn't it what facebook is doing with everyone's newsfeed?

        0 replies 0 retweets 2 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Simon Sarris‏ @simonsarris 3 Jul 2017
        Replying to @paulg

        You of all people should realize the insanity if you replace "news stories" with "startups." Both are a form of salient events.

        0 replies 0 retweets 2 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. trevor welch‏ @trevorwelch 3 Jul 2017
        Replying to @paulg @SingularMattrix

        my intuition is that like stock prediction the model would be very prone to overfitting and/or not finding solid correlation between X and y

        0 replies 0 retweets 2 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Diego Ventura‏ @colochef 3 Jul 2017
        Replying to @paulg

        Easily replicable with @monkeylearn An example:https://monkeylearn.com/blog/analyzing-10-years-of-startup-news-with-machine-learning/ …

        0 replies 0 retweets 2 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. Arch‏ @archer_mcgee 3 Jul 2017
        Replying to @paulg

        Not possible to do with just corpus of published text, requires knowledge of external events and context i.e: sentiment, relationships, etc

        0 replies 0 retweets 2 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