Robots that learn to kick-ass as they move🦿🍑 💥

Joined September 2007
19 Photos and videos
COMPACT-2-CRUISE
22
67
1,138
1,184,312
.@MarwanRefaat appreciate you stopping by HYPR—the team had a blast showing you HYPRACTIVE™. And thank you to Fractal Capital for checking out what we’re building up close and choosing to invest 🦾🔥
Drove through San Francisco with @TimKentleyKlay, co-founder and CEO of @hypr, while his AI, HYPRACTIVE, navigated downtown on 33 watts powering an NVIDIA Orin chip that runs HYPR's proprietary models built by just four engineers in two years, for under a million dollars. Tim is a Melbourne-born designer turned robotics CEO who co-founded Zoox, the first company to operate a purpose-built, fully autonomous robotaxi and scaled it to $3.2B. He envisioned the car becoming a character in 2011, and spent the next decade and a half making that real. 125 patents, $800M raised, and now CEO of HYPRLABS Inc - a small team coding a clean AI architecture and launching a completely new robot this summer. The whole industry is throwing tens of billions at problems HYPR is solving with a computer the size of your fist and a hot-glued camera.
1
1
26
608,172
COMPACT-MODE ENABLED
39
196
2,129
947,525
Roboparty happening over here...
1
3
74
124,764
We're excited to welcome Adam El Youmi to HYPRLABS as our newest AI Engineer! Master's in Mathematics from Centrale Nantes, Master's in Cybersecurity from Purdue — with deep expertise in AI, LLMs, and reinforcement learning. Glad to have him on the team. #AI #MachineLearning #HYPRLABS linkedin.com/in/adam-el-youm…
12
1,612
HYPRDRIVE™ and Run-Time Learning. Our CEO @TimKentleyKlay explains on @RoadToAutonomy how we use Guidance Feedback to power our continuous learning framework. x.com/RoadToAutonomy/status/… #AutonomousDriving #VisionOnly #MachineLearning
Self-Driving on 33 Watts: Live Demo with @TimKentleyKlay of @HYPR.
3
8
2,875
“The best way to train a neural network is at run-time, in-situ, on the robot.” Inside the HYPRDRIVE™ test vehicle: 5 cameras · NVIDIA Orin AGX · 33W compute Real-world autonomy in SF trained on ~1,600 hours of data. Learning happens while driving — not after. This is what run-time learning looks like. Watch the full demo with @TimKentleyKlay & @gbrulte on @RoadToAutonomy: x.com/RoadToAutonomy/status/…
Self-Driving on 33 Watts: Live Demo with @TimKentleyKlay of @HYPR.
1
3
10
1,796
10 billion miles of training data? Watch HYPRDRIVE™ autonomously driving in SF with just 10K miles of training data. Full demo is live on @RoadToAutonomy x.com/RoadToAutonomy/status/…
Replying to @pbeisel
Roughly 10 billion miles of training data is needed to achieve safe unsupervised self-driving. Reality has a super long tail of complexity.
5
1,724
17 Dec 2025
You asked. We drove. Following yesterday’s podcast, here’s the live, in-car drive with @timkentleyklay & @gbrulte.
Self-Driving on 33 Watts: Live Demo with @TimKentleyKlay of @HYPR.
4
9
1,463
HYPRLABS Inc. retweeted
Self-Driving on 33 Watts: How HYPR Labs Trained a Model for Just $850 @TimKentleyKlay, CEO & co-founder of @HYPR joined @gbrulte on The Road to Autonomy podcast to discuss how a team of four engineers achieved autonomous driving in San Francisco using just 33 watts of compute and an end-to-end neural network that prioritizes learning velocity over traditional simulation and mapping. Episode Chapters 0:00 Introduction to HYPRDRIVE 1:30 HYPRDRIVE 5:40 Learning Velocity 8:10 Building HYPR 12:23 Training the System 18:55 The Origins of the HYPR Approach 21:36 Building Trust 23:35 Simulation 2 7:07 $850 to Train the Model 30:44 HYPR Robots 33:22 Cameras 35:16 What's Next
1
7
17
3,408
16 Dec 2025
Introducing HYPRDRIVE™ our real-world continuous learning AI stack built on our belief that robots learn best when they learn as they move 🦾🎉 Check it out at hypr.co/hyprdrive
1
5
9
1,616
15 Dec 2025
Time to share what we've been working on: a new approach to robotic intelligence ⚡️ hypr.co is live.
5
8
993