Adnan Esmail
@adnan_esm
Followers
1K
Following
151
Media
13
Statuses
236
Co-Founder @physical_int | SVP Engineering @anduriltech, Former Hardware Technologies @Tesla
San Francisco
Joined March 2010
Reflecting on my @anduriltech journey feels surreal. Six years of relentless problem-solving, camaraderie, and defining moments. Grateful and proud to be able to share these stories for the first time.
12
22
282
RT @svlevine: Evaluating robotic foundation models is really hard — everyone has different robots, tasks, etc. We are releasing RoboArena a….
0
50
0
RT @KarlPertsch: We’re releasing the RoboArena today!🤖🦾. Fair & scalable evaluation is a major bottleneck for research on generalist polici….
0
81
0
RT @patrick_oshag: Anduril has become one of the most interesting company stories of this generation. @adnan_esm, who ran product engineeri….
0
30
0
RT @KTmBoyle: Great look behind the curtain at @anduriltech from @adnan_esm on Anduril’s product engineering machine. .
0
18
0
RT @joincolossus: The Amusement Park for Engineers. An exclusive peek behind the curtain of Anduril's product engineering machine. Featurin….
0
11
0
We asked π₀.₅ — trained mostly on data from other robots and the web — to “load the dishes” and “make the bed” in homes it had never seen. It parsed the instructions, planned, and executed end‑to‑end. This isn’t just a research milestone; it’s a real step toward
2
23
84
RT @bobmcgrewai: Don't get too excited about videos of humanoid robots dancing. Manipulation is the hard problem we need to solve to make….
0
48
0
Introducing "Hi Robot": we developed a way to let robots 'think through' complex tasks, breaking them into basic steps, modifying tasks on the fly, and adapting to user feedback. A major step in robot intelligence. Great work @lucy_x_shi and team at @physical_int!. Learn more.
0
1
11
It can fold laundry, scoop coffee, clean tables, and fine-tune on robots it’s never seen before. Now you can make it do more. 🤖 🦾.
0
0
0
π₀ is now open source. Model, weights, fine-tuned checkpoints—ready for you to build on. → GitHub: → Blog:
Many of you asked for code & weights for π₀, we are happy to announce that we are releasing π₀ and pre-trained checkpoints in our new openpi repository! We tested the model on a few public robots, and we include code for you to fine-tune it yourself.
2
0
8
RT @chelseabfinn: Disappointed with your ICLR paper being rejected?. Ten years ago today, Sergey and I finished training some of the first….
0
157
0
RT @TheHumanoidHub: Traditional tokenization methods for robotic actions struggle with high-frequency, dexterous tasks due to redundancy an….
0
63
0
Excited for the team to share FAST - our new robot action tokenizer - pulling off 5x improvements in VLA training speed. Congrats @KarlPertsch and team @physical_int.
There are great tokenizers for text and images, but existing action tokenizers don’t work well for dexterous, high-frequency control. We’re excited to release (and open-source) FAST, an efficient tokenizer for robot actions. With FAST, we can train dexterous generalist policies
1
0
9
RT @Ishansharma7390: Finally an AI that does laundry!🤯. Demo by Physical Intelligence. Would you buy a robot like this? .
0
1
0
RT @TheHumanoidHub: Anyone skeptical about AI’s ability to perform diverse physical tasks should watch this. Physical Intelligence's π₀ mo….
0
208
0