• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Alexandr Wang reportedly came up with the Muse feed

    Wang says agents with strong memory recommend content more like a friend who knows you, rather than serving up more of what you just clicked.

    AW
    MD
    2 Sources, ,

    TLDR

    Alexandr Wang says he came up with the Muse feed after noticing how differently agents with strong memory recommend content compared with existing recommendation systems. He likens their recommendations to a friend sending things they think you’d enjoy based on what they know about you. Wang calls the feed “just the beginning” and encourages people to try it.

    Combined views

    287.4K

    2 Sources, first seen 17d ago

    Combined views

    287.4K

    2 Sources, first seen 17d ago

    1.9K likes
    17d ago
    first seen 17d ago
    1.9K likes
    158 comments
    655 saves
    68 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    158 comments
    655 saves
    68 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @alexandr_wangfun fact: the muse feed was my idea (one of the few things that was) after realizing agents with strong memory recommend content to you in a very different way than existing recommendation systems they’re much closer to a good friend sending you things they think you might like based on what they knows about you, vs a slew of content related to what you just clicked. it’s just the beginning here, but very excited for people to try their muse feeds and see what they do with it!
    @mattdeitkeAI feeds in Muse feel like it itself could be a paradigm shift moment similar to Google -> ChatGPT but for social media. If you think about normal social media platforms, there’s a discrete number of posts and topics to choose from. With AI generated feeds, you move to an unlimited amount of content that can be produced targeted at your specific interests. With the ability to use web search and Instagram / FB, you can also ground the feed in the current zeitgeist of the day. We’re still quite early, but you can quickly imagine swarms of agents that do research and experimentation on your behalf to create a custom feed for you. For instance, you can imagine them finding products you might want, reading arxiv to find you the most interesting new papers relating to your interests, or even run scientific experiments and tell you about the results of them. For those that are interested in learning from their social feeds, this will be a beautiful thing. Feeds are interesting because they bring content to you, without you requesting it. It makes the cost of consuming it much lower than you needing to make a request, like you'd do if performing a search or asking an LLM. I think this is going to become a much bigger primitive in years to come.

    2 Sources

    @alexandr_wangfun fact: the muse feed was my idea (one of the few things that was) after realizing agents with strong memory recommend content to you in a very different way than existing recommendation systems they’re much closer to a good friend sending you things they think you might like based on what they knows about you, vs a slew of content related to what you just clicked. it’s just the beginning here, but very excited for people to try their muse feeds and see what they do with it!
    @mattdeitkeAI feeds in Muse feel like it itself could be a paradigm shift moment similar to Google -> ChatGPT but for social media. If you think about normal social media platforms, there’s a discrete number of posts and topics to choose from. With AI generated feeds, you move to an unlimited amount of content that can be produced targeted at your specific interests. With the ability to use web search and Instagram / FB, you can also ground the feed in the current zeitgeist of the day. We’re still quite early, but you can quickly imagine swarms of agents that do research and experimentation on your behalf to create a custom feed for you. For instance, you can imagine them finding products you might want, reading arxiv to find you the most interesting new papers relating to your interests, or even run scientific experiments and tell you about the results of them. For those that are interested in learning from their social feeds, this will be a beautiful thing. Feeds are interesting because they bring content to you, without you requesting it. It makes the cost of consuming it much lower than you needing to make a request, like you'd do if performing a search or asking an LLM. I think this is going to become a much bigger primitive in years to come.