←
Anna Walling50 posts
Anna Walling avatar

Anna Walling

@annawalling

building ops @physical_int. ex-chief of staff @Compound. people @CurologyUSA + @GustoHQ. retired professional baker 🍪

◷ Joined January 2012▧ 14 Photos and videos
Simon Mahns @ CoRL avatar
⟳ Anna Walling retweeted
Simon Mahns @ CoRL@nautsimon_·7h

π0.7 from @physical_int was built for robot arms, but with just 1.5 hours of driving data, it drove a real Tesla through multiple cone courses and topped our benchmark. 🚗 I think most people wouldn't expect a VLA/WAM to drive a car at all. Not only are these models pretrained primarly on teleop / egocentric data for (bi)manual style tasks, our action interface is [curvature, speed], which is out of distribution compared to the typical DoF of an arm or gripper. But we fine-tuned 6 of them, and every one was able to drive the Tesla. See more on our site!

Post attachment
Anna Walling avatar
Anna Walling@annawalling·Nov 13

hiring a GM for research ops! looking for someone who can manage managers, build great teams, solve hard problems, and create systems that absorb complexity. must also be fun. we're going to spend a lot of time together 😇 jobs.ashbyhq.com/physicalint…

Chelsea Finn avatar
⟳ Anna Walling retweeted
Chelsea Finn@chelseabfinn·Oct 13

The Pi API is officially in beta! 🤖 Many people have already been using it to fine-tune π models for their robots -- below are a few We’re hoping to expand testing significantly. Let us know if you are interested! Blog: pi.website/blog/api-beta Signup: pi.website/waitlist

0:40
Anna Walling avatar
Anna Walling@annawalling·Oct 14

collect demos → train → test on the robot → decide what to change → run it back. we do this a lot. now you can too. beta api waitlist is live 😎

Announcing the beta release of the Pi API. We’ve partnered with companies across diverse industries to adapt our models to their robots and applications, from harvesting strawberries to assembling servers. Now we’re opening access to more teams.

0:35
Quan Vuong avatar
⟳ Anna Walling retweeted
Quan Vuong@QuanVng·Oct 9

Congrats to @Ultraroboticsco on the raise! 🚀 Ultra and Pi have been working together to bring our models into real warehouses. We've gone from training ~1 policy per week to 8+, and improved autonomous performance from ~60% to ~95%. Really cool to see how quickly things can improve when you're iterating on models with real-world robot data.

Robotics has a distribution problem. Today, Ultra is announcing $62M in funding to solve it, including a $50M Series A led by @hiFramework. We believe that deployment is the bottleneck in robotics. It’s relatively easy to make a robot look impressive in a controlled environment. It’s much harder to put a robot into the open world, make it useful, keep it running, earn the trust of the people working alongside it, and do that over and over and over again. So that’s what we’re focusing on.

2:04
Sergey Levine avatar
⟳ Anna Walling retweeted
Sergey Levine@svlevine·Sep 30

π-0.7 API hackathon where we learn that in fact an excavator and a nerf gun are also robots kudos to @ActorLabs for the awesome event

Over the weekend, I put an unreleased checkpoint of π0.7 inside an excavator and placed 2nd at the @ActorLabs + @physical_int 36hr hackathon. With about an hour of embodied data (3 cameras and joystick values, no joint angles), the policy could continuously move dirt with a single prompt. This was so straightforward to get working (pi is cooking) we spent the rest of the hackathon mounting a Nerf minigun on the roof. We added a people searching/tracking + firing feature to prevent people from getting too close to the dangerous machinery (ai safety feature). Here’s how we built it + more details (data collection, hardware hax, sim2real, video of me getting shot)🧵

Post attachmentPost attachment
0:18
Y Combinator avatar
⟳ Anna Walling retweeted
Y Combinator@ycombinator·Aug 12

Robots can already fold laundry, make espresso, clean kitchens, and assemble things. The harder problem is getting them to do those tasks reliably, for long periods of time, without a human babysitting them. At Startup School 2026, @physical_int cofounder @chelseabfinn explains what it takes to build general-purpose robots that work in the real world. She shares how reinforcement learning pushed robot throughput up 2x, how their systems can run autonomously for hours, and why she believes robotics is entering its GPT era: moving from specialized models toward general-purpose systems that can work across tasks, robots, and environments. 00:00 — The State of Physical Intelligence 01:23 — What It Takes to Make Robots Useful 05:11 — The Reliability Problem 07:43 — Reinforcement Learning for Robotics 09:35 — Learning From Failures 12:43 — Training Robots to Improve Themselves 14:21 — Can a Robot Work for 13 Hours Straight? 17:36 — Why Robots Need Memory 21:22 — Building a General-Purpose Robot 25:02 — From Fine-Tuning to Out-of-the-Box Models 27:35 — Training on All the Data 30:20 — One Model That Beats the Specialists 31:21 — Compositional Generalization 37:49 — The GPT Era of Robotics 39:49 — Q&A

58:18
Anna Walling avatar
Anna Walling@annawalling·Apr 16

π*0.6 with memory: grilled cheese, π0.7: vegetables. unexpected transfer to healthier eating behaviors 🙃

We are especially excited about how π0.7 seems to exhibit emergent compositional generalization: it can put together skills it learned in new ways based on the prompt, for example to figure out how to use an air fryer to cook a sweet potato.

0:11
donald avatar
⟳ Anna Walling retweeted
donald@donaldjewkes·Apr 16

POV you doordashed an air fryer and it's about to get zero-shot

Post attachment

Our newest model, π0.7, has some interesting emergent capabilities: it can control a new robot to fold shirts for which we had no shirt folding data, figure out how to use an appliance with language-based coaching, and perform a wide range of dexterous tasks all in one model!

4:02
Lane Burgett avatar
⟳ Anna Walling retweeted
Lane Burgett@laneburgett·Mar 9

I'm extremely excited to announce that we've successfully inferenced π0.5 on our excavator! We've collected a massive corpus of real-world data with natural language labels from operators in the industry and are using it to create some really cool policies. Here's our first demo of it successfully completing a task with just 200 trajectories. More on the way :) Read our blog post: labs.actor/research/vla-exca… @physical_int

1:04
Anna Walling avatar
Anna Walling@annawalling·Mar 3

Personally consumed an alarming number of grilled cheeses throughout this project. Now you can too 😀

We’ve developed a memory system for our models that provides both short-term visual memory and long-term semantic memory. Our approach allows us to train robots to perform long and complex tasks, like cleaning up a kitchen or preparing a grilled cheese sandwich from scratch 👇

2:16