Kavin Raj

Building Fidelity dynamics | Stay curious | prev @Upsurgelabs |🇮🇳

[Kavin Raj @kavinrajkr]

You are not your results; you are your efforts.

[Kavin Raj @kavinrajkr]

I won’t be standing anywhere near it during calibration

[Chetan @chetan_]

who's making buff robots?

[Kavin Raj @kavinrajkr]

@sssssshwan @chris_j_paxton Amazing work!

[Naval @naval]

It's the Age of Builders.

(sorry financiers and talkers)

[Kavin Raj @kavinrajkr]

@VectorWang2 amazing work!

[Kavin Raj @kavinrajkr]

@furongh @TX_Leo_Wang Sounds cool!

[Kavin Raj @kavinrajkr]

@bhoomikacodes damn - very cool!

[Humanoids daily @humanoidsdaily]

In a masterclass at @Sequoia AI Ascent, @drjimfan laid out the "Great Parallel": how robotics is speedrunning the LLM playbook.

🔹 VLA → WAM: Moving from language-heavy models to "World Action Models" that dream in physics.
🔹 Teleop → EgoScale: Replacing manual data with human egocentric video.
🔹 Simulation 2.0: Using neural simulators like DreamDojo to turn compute into environments.

"Our generation was born too late to explore the earth and too early to explore the stars. But we are born just in time to solve robotics."

He believes that robots will pass the Physical Turing Test in the coming 2–3 years.

[Kyle Vedder @KyleVedder]

also

if you know how to post train a policy you can always pivot to being a neodeployment team later

with your ops cost paid for by your competitors 🧠

[Kyle Vedder @KyleVedder]

if you can show videos of your policy working, we don’t need to QA your data

it’s already proven to be good and you can charge accordingly

[Kyle Vedder @KyleVedder]

why are no data factories selling post-training data?

take a base policy, pick a task, dagger it to three 9s reliability, and sell the dagger data as a premium bundle

pretraining data is a commodity slop game, post-training is value add

but no one’s doing it yet 🤡

[Can Vardar @icanvardar]

if you’re a guy in your 20s, build a robotics startup

go into debt if you have to

[Lukas Ziegler @lukas_m_ziegler]

🔥 JUST IN:

Open-source robotics dataset from 100% real-world scenarios! 🤯

Chinese robotics company @AGIBOTofficial just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions.

Built entirely from real-world environments: commercial spaces, and homes.
Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data.

Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced.

The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks.

First-person teleoperation lets operators control the robot from its perspective.
The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration.

The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes.

After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds.

Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. 🇨🇳

Learn more here: https://t.co/iIOcEs4AnN

~~
♻️ Join the weekly robotics newsletter, and never miss any news → https://t.co/GoA3ZuwoPB

[Kavin Raj @kavinrajkr]

Only few can understand this....

[Richard Burton @Ricburton]

Superhuman crash avoidance in a Tesla

Imagine this performance for all areas in life

That is what roboticists are promising us

[Nick Khami @skeptrune]

"claude usage limit reached. your limit will reset at 7pm"

[Bryson Jones @brysonkjones]

Today I’m releasing an open-source implementation of Multitask Diffusion Policy model, most widely seen deployed on the Boston Dynamics Atlas Humanoid Robot!

Check out the demo + some cool takeaways

[Kavin Raj @kavinrajkr]

@brysonkjones These are amazing insights, very useful!

[Kavin Raj @kavinrajkr]

It never happened this fast.

[Kavin Raj @kavinrajkr]

@VilleKuosmanen Think hard!

[Kavin Raj @kavinrajkr]

@sanskxr02 @gbrl_dick It’s harder than we think lamo!