Posts like this is absolute gold and the reason I love this platform. Must read for any hardware founder. I'm not going to summarize, go ahead and read the whole thing.
@typesfast talks about global trade in a way that's even more engaging than his takes on making money. Genuinely fascinating stuff. Would love to hear him cover the Hansa one day.
My first interview with Ryan Petersen (@typesfast), Founder of Flexport.
0:03 Pablo Escobar was a logistics guy
2:29 The explosion in tariff fraud
8:58 The Dutch East India Company
11:20 History of global trade
14:39 1,000x spice markup
17:53 The British East India Company
24:02 How the British got 20% of China addicted to opium
27:44 The Forbes family & opium trade
30:40 Jewish trading networks
37:33 Itโs illegal to criticize the King of Thailand
38:58 Strait of Hormuz
45:58 Maritime chokepoints
We are back again :) After three weeks of quiet building.
Introducing Genesis World 1.0, our latest simulation platform, the second release in our full-stack suite. Open-sourced.
Robotics is still bottlenecked by the 1ร speed of the physical world. Every model, checkpoint, and data recipe eventually needs to be tested on physical hardware, slowly, expensively, and with limited coverage.
One hour in reality can become 100 days in simulation. That is how robotics model iteration moves from a wall-clock bottleneck to a compute problem.
To make this work, simulation has to be both fast and trustworthy.
Over the past year, we rebuilt the entire stack: a GPU-accelerated cross-platform compiler, penetration-free multi-physics contact solvers, unified rigid and deformable physics, and a photo-realistic renderer purpose-built for physical AI applications.
We built Nyx, a high-performance path-traced rendering engine for robotics application.
Genesis World 1.0 achieves near realtime performance with our latest development for penetration-free IPC solver, supporting various types of deformables beyond rigid bodies. It supports contact-rich, dexterous manipulation simulation across different embodiments: unitree, sharpa, wuji, genesis hand and various types of grippers.
Under the hood is Quadrants, our effort in pushing forward cross-platform GPU-accelerated computation. Quadrants started as a fork of Taichi, and we rebuilt most of the critical parts for optimizing simulation workloads, giving 10x faster launch time and up to 4.6x runtime performance compared to the initial Genesis release.
Together, they bring us to an unprecedentedly low sim-to-real gap, enabling zero-shot real-to-sim model evaluation and much faster iteration of GENE.
All available today.
Genesis World 1.0: https://t.co/aknCM3eqws
Quadrants: https://t.co/uXqPNI4cb6
Nyx: https://t.co/R8j0djqGnV
Excited to introduce #TruckDrive ๐ at #CVPR2026: a new long-range driving dataset built specifically for long-range truck autonomy, where safe braking and anticipatory planning demand perception hundreds of meters ahead, far beyond existing robotaxi datasets.
๐ฆ TruckDrive includes:
๐น 475K samples, with 165K densely annotated frames
๐น Benchmarks for end-to-end driving, tracking, planning, depth estimation, and up to 1,000m for 2D detection and 400m for 3D detection ๐๐ฏ
๐ฐ๏ธ A purpose-built long-range sensor suite:
๐ธ 7 long-range FMCW LiDARs (range + radial velocity)
๐ธ 3 high-res short-range LiDARs
๐ธ 11ร 8MP surround cameras for short and long-range๐ท
๐ธ 10ร 4D FMCW radars ๐ก
โ ๏ธ Key finding: current state-of-the-art models break down at long range
๐ with 31% to 99% drops on 3D perception tasks beyond 150m. TruckDrive exposes a long-range generalization gap that current architectures and training signals are not closing yet - a benchmark for the next generation of long-range highway autonomy research ๐
๐ Project and Data: https://t.co/fNzDCbGQRQ
Fun work together with @torc_robotics led by Filippo Ghilotti, Edoardo Palladin, Samuel Brucker, Adam Sigal, and Mario Bijelic.
Genesis team became publicly active lately, and that's very good news for the robotics community. They introduced Genesis sim as a concept back in 2024, and then went quiet. Now they are back with https://t.co/877Zo4MQgu and Genesis World https://t.co/O7s4mpV21H
I think people don't appreciate enough how hard this is. I've only caught a glimpse of the stream, but several important things are clearly being done right:
The robot got to the line on its own. Robots coordinate battery levels across the fleet, when one gets low, another one comes up to take over. No visible overheating, no fatal pipeline crashes from random segfaults, no memory leaks that only surface after hours of operation. Pipeline latency looks fine. Control looks solid: coordinating so many DoF is no joke. Manipulation has room for improvement, but that's understandable.
@adcock_brett , would love to see a highlights video after this ends! Things like robots walking in/out, challenging moments, out-of-distribution problems, unexpected behavior and basic stats such as accuracy. Keep it up.
Details on what's going on:
> Our original goal was an 8-hour run - we wanted to run nonstop and fully autonomous. Since then, we made the decision to keep the party going. Weโre now over 48 hours of nonstop autonomous operation without a failure to perform the use case. This is uncharted territory
> The task is small package sorting. F.03 detects the barcode, picks up the package, and reorients it barcode face-down onto the conveyor
> Humans average around 3 seconds per package. F.03 is now around human parity. The robots are reasoning directly from camera pixels in the robot head
> The robots are fully autonomous running Helix-02, our in-house neural network running entirely onboard F.03. There is no teleoperation - every action comes directly from Helix-02
> If the robot gets stuck or the AI policy goes out of distribution, Helix triggers an automatic reset. Youโll occasionally see this happen during the livestream
> YouTube commenters started naming the robots Bob, Frank, Rose, and Gary this week, so we added name tags to each robot
> If a robot has a software or hardware issue, it autonomously leaves for maintenance and another robot takes over. We run our labs at Figure this way to maximize uptime. We havenโt had a failure yet, but statistically we probably will at some point
We are now running this until a failure to perform the use case!
Grok is actually amazing. The selling point for me is the Ara voice + argumentative personality. It pushes back hard and the voice itself is superb, it handles my Russian accent like a charm. And it feels like a real conversation in a way that's hard to describe.
There is a computer vision course I wish I had taken properly before starting out in perception: https://t.co/VPHOBkRxBO
No, it is not CS231N, the famous CNN-heavy course by @karpathy. It is CS231A, its geometry-first counterpart. You need to know the fundamentals: camera models, calibration, SfM, stereo/mono depth estimation, scene flow, etc. Of course, end-to-end transformers can learn a lot of this on their own, but at least you need to know what is going on and why.
Amazing course notes and assignments. If you complete the course and can reimplement something like LSS (Lift, Splat, Shoot), you'll be well positioned for the job regardless of current trendy architectures. Do not skip this part.
The bottleneck for AI engineers has shifted from producing code to verifying it. And verification is getting really hard: ML bugs don't crash anything, they just silently train the wrong thing. And no, you can't catch what you don't already understand.
Years ago at Yandex I interviewed ML candidates with exactly this task: here's the training code, find the subtle bugs. Back then it was a filter for senior engineers, now it's the core of the trade. What a time to be alive.
Progress podcast's signal to noise ratio is extremely high. And this is only episode two. Keller and Ryan are ideal role models for any serious entrepreneur: people who take real risk, build real businesses, and compound company value year after year for decades. @fuelfive, outstanding work on guest selection, please keep it up!
The Silk Road made everyone rich, and then it killed half of them.
Progress ep02 is live with @typesfast of @Flexport.
We discuss why the global economy is as fragile as ever, what it takes for America to build again, and whether AI needs its own god.
@NikolausWest@rerundotio@maticrobots Also I noticed Rust attracts enthusiastic folks who view programming as a craft rather than just a way to earn money. Ruby and Rails got pretty much the same kind of people in the 2010s.
Mark my words: Rust is about to explode in robotics โ and coding agents are the main driver. @rerundotio and @maticrobots were right about Rust from the beginning. The #1 requirement for agentic coding (e.g., in Claude Code) is a tight feedback loop with clear error signals. Rust's compiler is perfect for this: if it compiles, it's (mostly!) memory-safe and data-race-free. C++ lets agents generate code that compiles fine and segfaults at runtime. That's a terrible feedback loop.
Rust's package ecosystem (https://t.co/XO7qobTqVc + Cargo) is another huge advantage. Agents can discover, add, and build dependencies with zero human intervention. There's nothing even close in the C++ world, I'm sure even C++ guys are not going to argue with this.
"But C++ has all the libraries!" - this is true today. But the libraries that matter at runtime (inference, sensor drivers, motion planning) are increasingly available. And you don't need PyTorch at runtime.
"But there's way more C++ to train on!" - there's also way more C++ footguns to learn from. Quality > quantity. Rust's smaller, more modern corpus arguably produces better output for agents with fewer hallucinated patterns.
OK, what about hiring? Agents dramatically reduce the importance of team size. One strong engineer with agents writing Rust > a team writing C++ and debugging segfaults in runtime. Also, people really love learning and writing in Rust!
@paveliakovenko Yes, for a really good world model they need to simulate other sensors rather than just pure vision. Sound and voice should also be simulated!
There is one thing I'm really certain about after my years in self-driving / physical AI โ there is no safe self-driving and robotics without an extremely high-fidelity neural simulation.
The dreaded long tail of self-driving is not solvable by just "driving more". Right now, simulation and world modeling is really the Holy Grail of robotics. Kudos to @Waymo and @GoogleDeepMind, this is an amazing application of Genie 3. https://t.co/sjypEY1GvU
Just a couple hours ago, @karpathy mentioned the revival of RSS and making an RSS reader for popular HN blogsโso I vibe-coded one in an hour with a nice TUI in Rust (I know zero Rust).
It works exactly how I want: extremely minimal, distraction-free, with powerful navigationโand any feature you want is delivered on the fly. Perfect for exploring these blogs, most of which I'd never read before.
Not sure if I should open source it or just share the https://t.co/oBdcRzTYVq. We live in crazy times.
Finding myself going back to RSS/Atom feeds a lot more recently. There's a lot more higher quality longform and a lot less slop intended to provoke. Any product that happens to look a bit different today but that has fundamentally the same incentive structures will eventually converge to the same black hole at the center of gravity well.
We should bring back RSS - it's open, pervasive, hackable.
Download a client, e.g. NetNewsWire (or vibe code one)
Cold start: example of getting off the ground, here is a list of 92 RSS feeds of blogs that were most popular on HN in 2025:
https://t.co/dwAiIjlXet
Works great and you will lose a lot fewer brain cells.
I don't know, something has to change.