Log inSign up
Image
user avatar
Andy Zeng
@andyzengineer
Building robot foundation models @GeneralistAI. Prev @GoogleDeepMind, PhD @Princeton. One experiment away from magic. ✗DMs → email
andyzeng.github.io
Joined September 2017
629
Following
10K
Followers
RepliesArticlesMedia
  • Pinned
    user avatar
    Andy Zeng
    @andyzengineer
    Apr 2
    GEN-1 is now available today to our Early Access Partners. Let’s build.
    user avatar
    Generalist
    @GeneralistAI
    Apr 2
    Introducing GEN-1. Our latest milestone in scaling robot learning. We believe it to be the first general-purpose AI model to master simple physical tasks. 99% success rates, 3x faster speeds, adapts in real time to unexpected scenarios, w/ only 1 hour of robot data. More🧵👇
    Image
    00:00
  • user avatar
    Andy Zeng
    @andyzengineer
    May 12
    Decades of hardware development led to strong, fast, and precise robot arms. The moment we can put in general intelligence in these things, we can leverage the full spectra of capabilities that they were always meant to capture. We’re betting on a future where robot hardware
    Image
    00:00
    Image
    01:15
    user avatar
    Generalist
    @GeneralistAI
    May 12
    GEN-1 delicately arranges potato chips, and lifts a heavy bag of potatoes — from a gentle touch to a strong grip. Read more about Gen-1 in our blog posts in the comments below ↓
  • user avatar
    Andy Zeng
    @andyzengineer
    Apr 30
    For the avid viewer -- there’s a brief moment when the robot loses it’s grip on the head of a ziptie, and so it decides to use the other hand to help readjust the grip for the pull. It’s gnarly passing by our robots everyday, and catching these random glimpses of improvisational
    Image
    00:00
  • user avatar
    Andy Zeng
    @andyzengineer
    Apr 21
    If anyone’s creating a benchmark for frontier physical AI models, this task is a great one to add to the roster. Sensorimotor end-to-end policies must exhibit the long-term visual memory to track and reason about where the object might be. It’s also harder to “cheat” on this
    user avatar
    Generalist
    @GeneralistAI
    Apr 21
    GEN-1 plays the 🐚 shell game, trained on just 1 hr of robot data. It also generalizes to unseen objects, like @BerkayAntmen 's car keys. Physical AI models should be capable of benchmark tasks like this one. It's interesting for the all the reasons @RhodaAI calls out --
    Image
    00:00
  • user avatar
    Andy Zeng
    @andyzengineer
    Apr 13
    The first time we rolled a robot into a new warehouse, it didn’t perform as well as we expected. It took us an entire day of debugging, before we realized it was something simple… the cameras were wired completely wrong. 🤦 Left camera to right gripper 🔀 right camera to left

  • See @andyzengineer's full profile

    Sign up
    Log in