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

    Ao Qu Posts Tweet on Self-Evolving AI

    MIT PhD candidate shares link to article about his AI research on X.

    RS
    PL
    YO
    9 Sources, 29d ago, first seen 29d ago

    TLDR

    The evidence packet records a tweet authored by the X user @ao_qu18465, identified as Ao Qu. He is described as a PhD student affiliated with MIT, the MIT Institute for Data, Systems, and Society, and the MIT Media Lab. His background includes prior experience at ByteDance Seed. The tweet contains a link to an article hosted on X at the provided URL. No further content from the tweet or article is included in the packet. This post is categorized under the AI topic.

    Combined views

    176.7K

    9 Sources, first seen 29d ago

    Combined views

    176.7K

    9 Sources, first seen 29d ago

    463 likes
    463 likes
    24 comments
    509 saves
    145 reposts
    24 comments
    509 saves
    145 reposts

    Sentiment

    Positive94.4%5.6%Negative

    Summary

    Sentiment

    Positive94.4%5.6%Negative

    Many accounts welcomed Reef's open-source release for its rapid GitHub traction and production-data loop that evolves agents across weights, prompts, and memory, while one reply raised write-back issues seen in real projects.

    Based on 23 sentiment-bearing replies from 18 accounts across 3 conversations.

    Summary

    Many accounts welcomed Reef's open-source release for its rapid GitHub traction and production-data loop that evolves agents across weights, prompts, and memory, while one reply raised write-back issues seen in real projects.

    Based on 23 sentiment-bearing replies from 18 accounts across 3 conversations.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    9 Sources

    @ao_qu18465https://x.com/i/article/2094850055132024832
    @hanzheng_7🚀One of the biggest questions for AI agents is whether they can continue expanding their capabilities after deployment. Deployment brings the experience needed to keep improving. As @ilyasut has argued, future intelligent systems should learn from deployment. But this requires more than a new learning algorithm. It requires turning the serving stack itself into a learning layer: collecting live experience, turning it into updates, and safely bringing those updates back into serving. That’s why we built Reef. Reef is open-source infrastructure for continuously evolving agents at live deployment. To our knowledge, it is the first open-source infrastructure designed to evolve both model weights and the agent harness from deployment experience. Not just weights, but also prompts, memory, skills, tools, and orchestration. Reef already supports: 🧠Model evolution: SAO, TTT-Discover, OpenClaw-RL, with more recipes coming. 🛠️Harness evolution: SkillClaw, Meta-Harness, and a general harness-evolution engine built on Cordis, with native support for pi @pidotdev , OpenCode @opencode , and more harnesses coming. With Reef, inference is no longer the end of the pipeline. It becomes part of a continual loop: serve → learn → evolve → serve again. Reef is fully open source. We would love you to try it, build on it, and tell us what is missing! ⭐ GitHub: https://github.com/Human-Agent-Society/reef. 💬 Discord: https://discord.com/invite/5y8e5f937k. #AgenticAI #llms
    @ScobleizerRT @hanzheng_7: 🚀One of the biggest questions for AI agents is whether they can continue expanding their capabilities after deployment. De…
    @pliang279RT @MaxForAI: 🚨Agent 开始真的学会自己养自己了。 今天,一个叫 Reef 的持续学习基础设施正式开源。 它由 Human-Agent-Society 团队开源,他们说一群来自 MIT、NUS 等机构的研究者,核心成员包括 Ao Qu、Han Zheng、…
    @yoheinakajimalooks cool
    @yhfchitandaCheck how Reef serves your self-improving agents uninterruptedly while learning! https://x.com/i/article/2095935379518226432

    9 Sources

    @ao_qu18465https://x.com/i/article/2094850055132024832
    @hanzheng_7🚀One of the biggest questions for AI agents is whether they can continue expanding their capabilities after deployment. Deployment brings the experience needed to keep improving. As @ilyasut has argued, future intelligent systems should learn from deployment. But this requires more than a new learning algorithm. It requires turning the serving stack itself into a learning layer: collecting live experience, turning it into updates, and safely bringing those updates back into serving. That’s why we built Reef. Reef is open-source infrastructure for continuously evolving agents at live deployment. To our knowledge, it is the first open-source infrastructure designed to evolve both model weights and the agent harness from deployment experience. Not just weights, but also prompts, memory, skills, tools, and orchestration. Reef already supports: 🧠Model evolution: SAO, TTT-Discover, OpenClaw-RL, with more recipes coming. 🛠️Harness evolution: SkillClaw, Meta-Harness, and a general harness-evolution engine built on Cordis, with native support for pi @pidotdev , OpenCode @opencode , and more harnesses coming. With Reef, inference is no longer the end of the pipeline. It becomes part of a continual loop: serve → learn → evolve → serve again. Reef is fully open source. We would love you to try it, build on it, and tell us what is missing! ⭐ GitHub: https://github.com/Human-Agent-Society/reef. 💬 Discord: https://discord.com/invite/5y8e5f937k. #AgenticAI #llms
    @ScobleizerRT @hanzheng_7: 🚀One of the biggest questions for AI agents is whether they can continue expanding their capabilities after deployment. De…
    @pliang279RT @MaxForAI: 🚨Agent 开始真的学会自己养自己了。 今天,一个叫 Reef 的持续学习基础设施正式开源。 它由 Human-Agent-Society 团队开源,他们说一群来自 MIT、NUS 等机构的研究者,核心成员包括 Ao Qu、Han Zheng、…
    @yoheinakajimalooks cool
    @yhfchitandaCheck how Reef serves your self-improving agents uninterruptedly while learning! https://x.com/i/article/2095935379518226432