Leave it to Sunday

Redwood City, CA
Introducing ACT-2 Preview, the world’s first robotics model that works in your home. 99% success rate, fully autonomous in unseen homes. Zero data from you.
66
164
1,225
235,164
we’re taking human-robot interaction very seriously
19
15
370
17,805
Sunday retweeted
Sunday Robotics' Tony Zhao runs a fully autonomous robot demo live and unscripted, and it corrects itself every time you mess with it: @brexton: "I want to confirm for the audience right now that this is fully autonomous. There's no teleoperation, no one behind the curtain, and this is real time. And we did not prepare this demo before. Why do you think seeing real-time demos is so rare for robotics? What the audience is seeing right now is not that common." @tonyzzhao: "In order for a live demo to work, it's really stressing all parts of the system. From the bottom is the reliability of the hardware, then the software system, then the model. Because we're a full-stack company, we're able to do excellent work across all of them. We have these robots running pretty much every day, and it just keeps getting better as they practice." @brexton: "So kids can bump into Memo, people can drop clothes, and it will correct itself just on the fly." @tonyzzhao: "Act Two is the first robotic policy that can handle the diversity of homes in a way that is this reliable. You can see as I'm twisting it, if I twist it in again, it will keep doing it. So Memo has infinite patience." @sundayrobotics
14
43
377
135,521
Sunday retweeted
friends and family of memo
6
6
88
47,230
Sunday retweeted
Sunday Robotics CEO @tonyzzhao believes home robots only need to master a handful of chores before they become indispensable. "What is the minimum number of tasks that a robot needs to do to justify its own existence so that people love having it in their homes? I actually think the list is pretty short. The tasks are pretty repetitive. You just need to learn it and just keep doing that over and over again, like folding shirts or loading dishwashers."
Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.
8
20
210
66,132
Sunday retweeted
Nobody, not even these guys, has the Neocambrian explosion of substrate independent intelligence priced in. Prepare for a robot in every home. Not just sooner than we think -- sooner than we are *able* to think.
Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.
24
47
931
95,412
Salute to Sunday folks 🫡 It is amazing as well as interesting to see how much solid engineering is needed for smooth and reliable deployment
We just hit a weird milestone: our model became more reliable than your average home WiFi. Just like everybody else, we thought cloud inference was the obvious choice. Yet 2 days into the ACT-2 eval, our mind completely changed. If our hero @ArpitKalla didn’t cook, this video wouldn’t exist 🧵
4
3
50
10,331
Sunday retweeted
1/N Two years ago, we recruited our first Memory Developer off Craigslist and onboarded them in a public library. Today, more than 1,000 Memory Developers have helped us build the data engine behind ACT-2. Here's how we got from that library to here 🧵
12
33
217
96,001
Sunday retweeted
We just hit a weird milestone: our model became more reliable than your average home WiFi. Just like everybody else, we thought cloud inference was the obvious choice. Yet 2 days into the ACT-2 eval, our mind completely changed. If our hero @ArpitKalla didn’t cook, this video wouldn’t exist 🧵
88
165
1,872
420,112
Sunday retweeted
One year ago, I wouldn't have imagined that laundry folding would be the first "solved" task for home robots. The world is moving soooooo fast!
Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.
7
18
236
75,289
Sunday retweeted
The money shot
Replying to @tonyzzhao
Quantitatively, we measure the generalization gap as the difference between in-domain and out-of-domain performance. As we scale up pretraining, the gap falls sharply. This makes in-house performance a reliable predictor of performance in the wild.
2
13
106
24,690
Sunday retweeted
why so much hype around robotics, but no robots in homes yet? insufficient generalization and robustness to deploy. that’s changing, and the way we measure robotics needs to change too! research update from the team of 🧑‍🍳 @sundayrobotics, and when something is really “SOLVED”
Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.
15
8
158
32,567
Sunday retweeted
amazing progress
Introducing ACT-2 Preview The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes. Zero shot, real unseen homes, 99% success rate.
2
3
57
13,486
Replying to @tonyzzhao
So cool, can't wait to have one at my place
2
2
74
9,787
We had fun testing Memo against every household scenario imaginable: - Picking up clothes off the ground - Handling baby wear to 8XL shirts - Reacting to adversarial disturbances and lighting
2
9
91
11,566
The core breakthrough behind ACT-2 is a general training recipe. Just like LLMs, scaling data and compute gives us predictable improvements. Unlocking one Solve accelerates the timeline of the next Solve. The same ACT-2 model is now learning many new tasks:
3
5
65
5,376