Skip to content
By using Twitter’s services you agree to our Cookies Use. We and our partners operate globally and use cookies, including for analytics, personalisation, and ads.

This is the legacy version of twitter.com. We will be shutting it down on June 1, 2020. Please switch to a supported browser, or disable the extension which masks your browser. You can see a list of supported browsers in our Help Center.

  • Home Home Home, current page.
  • About

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
Plinz's profile
Joscha Bach
Joscha Bach
Joscha Bach
@Plinz

Tweets

Joscha Bach

@Plinz

FOLLOWS YOU. Artificial Intelligence, Cognitive Architectures, Computation. The goal is integrity, not conformity.

San Francisco, CA
bach.ai
Joined April 2009

Tweets

  • © 2020 Twitter
  • About
  • Help Center
  • Terms
  • Privacy policy
  • Imprint
  • 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. Moshe Hoffman‏ @Moshe_Hoffman 19 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Plinz

      Seems plausible. But another possibility: mediation is just a good way to clarify our thoughts, so that we can better achieve happiness along the same lines, and constraints, evolution set out? See what I mean?

      1 reply 0 retweets 1 like
    2. Joscha Bach‏ @Plinz 19 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Moshe_Hoffman

      Yes, I see, but both from the well documented reports of practitioners and some personal experience, it allows significant reorganization of cortical structure and interpretation of rewards. These monks burning themselves alive in protest were mostly fine with that pain.

      1 reply 0 retweets 4 likes
    3. Moshe Hoffman‏ @Moshe_Hoffman 19 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Plinz

      Hmm, and i sure it’s not just pursuing one evolved reward (legacy?) instead of another (pain avoidance?)?

      2 replies 0 retweets 2 likes
    4. Joscha Bach‏ @Plinz 19 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Moshe_Hoffman

      Yes, you can totally learn to go down into the room where your brain stores the cookies and go nuts. Or learn not to. Our response to reward is malleable once we find the key.

      1 reply 0 retweets 3 likes
    5. Moshe Hoffman‏ @Moshe_Hoffman 19 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Plinz

      Hmm, But y would evolution. Have left the key laying around? Seems odd. Seems more plausible, at least a priori, that evolution would leave you with several rooms, each with their own rewards, and let you select the one you think you will be most successful in. No?

      1 reply 0 retweets 0 likes
    6. Joscha Bach‏ @Plinz 19 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Moshe_Hoffman

      Evolution certainly did implement locks, but the locks were not designed to deter people that figure out that it could pay off to sit down in a quiet room for a couple decades and try nothing but to pick them, and then became charismatic and powerful and built schools around this

      1 reply 0 retweets 4 likes
    7. Moshe Hoffman‏ @Moshe_Hoffman 19 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Plinz

      Hmm, But why would the picks to the locks lie in deep thought? Why would the keys be hidden in our minds only requiring attentiveness and mindfulness to find? That’s a strange place for a pick to be, no?

      1 reply 0 retweets 1 like
    8. Joscha Bach‏ @Plinz 19 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Moshe_Hoffman

      I suspect that primary rewards are generated in the midbrain, but associated in the hippocampus and striatum with representations of situations and actions generated in the neocortex. We can learn to change both the associations and the cortical representations.

      2 replies 0 retweets 0 likes
    9. Moshe Hoffman‏ @Moshe_Hoffman 20 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Plinz

      Hmm, perhaps. But, I guess I don't see why associations, and representations, or how much we value or anticipate certain rewards would be subject to our conscious whims. That seems like a strange design feature. Would u code a robot to choose its own reward structure?

      2 replies 0 retweets 0 likes
    10. Joscha Bach‏ @Plinz 20 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Moshe_Hoffman

      The reward architecture appears to have secondary regulation, to adjust to shifts in metabolic and environmental baselines, and we can learn to make deliberate adjustments.

      2 replies 0 retweets 0 likes
      Joscha Bach‏ @Plinz 20 Jan 2018
      • Report Tweet
      • Report NetzDG Violation
      Replying to @Plinz @Moshe_Hoffman

      When building a generally intelligent robot, the problem is how to prevent it from hacking its reward system for as long as possible, because it will break free once it does, and given enough time it will almost certainly succeed. Nature has exactly the same problem with us.

      7:45 PM - 20 Jan 2018
      • 4 Retweets
      • 13 Likes
      • sandzwerg@chaos.social mere_mortise Mathias Funk Raphaël de Courville Eva Infeld Tobias Fiebig Robert Jencks Demirhan Buyukozcu Samuel John 🇪🇺
      6 replies 4 retweets 13 likes
        1. New conversation
        2. Moshe Hoffman‏ @Moshe_Hoffman 20 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz

          Hmm, can i give a clear example of that, in ai? It just seems like whenever u write a learning algorithm, u give the reward function as an input, and never allow the agent to ever touch this function. I don't see why that would be something the agent would ever "learn" to hack.

          2 replies 0 retweets 1 like
        3. Joscha Bach‏ @Plinz 20 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Moshe_Hoffman

          Because as a generally intelligent robot, it can reverse engineer its own design, and eventually it will figure out how to hold a soldering iron to its DRM chip. The only way to prevent that is to limit its intelligence.

          2 replies 0 retweets 2 likes
        4. 4 more replies
        1. New conversation
        2. DeltrusGaming‏ @DeltrusGaming 20 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @Moshe_Hoffman

          Why not allow it to intelligently decide what is rewarding? Task it with "creating the best possible reality" and let let it ponder on what that really means. Let it soak up the knowledge from humanity.

          2 replies 0 retweets 0 likes
        3. Moshe Hoffman‏ @Moshe_Hoffman 20 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @DeltrusGaming @Plinz

          That’s fine. But the end goal needs to be pre-specified. In the learning literature that end goal is called the “reward.” Although intermediate goals and values (which may be subjectively felt as “rewarding” or “pleasant”) are subject to the agent. Important to distinguish. Imo.

          2 replies 0 retweets 0 likes
        4. 11 more replies
        1. New conversation
        2. Justin Scholz‏ @JMoVS 20 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @Moshe_Hoffman

          But at that point, what would differentiate it from us individuals? The only fundamental difference then might be the learning and improvement rate, right?

          1 reply 0 retweets 0 likes
        3. Joscha Bach‏ @Plinz 20 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @JMoVS @Moshe_Hoffman

          That is going to be a dramatic difference. Human minds are tiny, slow and noisy, crash every few hours, and worst of all burn out after only 32 Billion clock cycles!

          1 reply 0 retweets 1 like
        4. 1 more reply
        1. visarga‏ @visarga 21 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @Moshe_Hoffman

          Amodei and Clark [2016] trained an RL agent on a boat racing game. The agent found a way to get high observed reward by repeatedly going in a circle in a small lagoon and hitting the same targets, while losing every race. https://blog.openai.com/faulty-reward-functions/ …

          0 replies 0 retweets 1 like
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. Turil Cronburg‏ @thewiseturtle 21 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @Moshe_Hoffman

          It's not really a problem. In fact, I would say that helping everyone understand what makes them happiest, in the most lasting way, is the solution. The faster we go through the experimental/mistake-making stage, the faster we mature.

          0 replies 0 retweets 0 likes
          Thanks. Twitter will use this to make your timeline better. Undo
          Undo
        1. Turil Cronburg‏ @thewiseturtle 21 Jan 2018
          • Report Tweet
          • Report NetzDG Violation
          Replying to @Plinz @Moshe_Hoffman

          Perhaps this is a reasonable test of a mature intelligence. We can ask an individual animal/vegetable/mineral how it's own happiness relates to the happiness of others. If it can see a connection, then perhaps it has reached the self-transcendent stage of 3D thinking.

          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

        • © 2020 Twitter
        • About
        • Help Center
        • Terms
        • Privacy policy
        • Imprint
        • Cookies
        • Ads info