FOLLOW A QUESTION FURTHER

Library

Practical lessons, original research, and the details that make systems work.

Refine your reading
47 articles

Articles

Migration
GitHub Engineering· Josh Black

Improving site performance by shipping more CSS (opens in a new tab)

The Primer Design System powers many of the experiences you see on GitHub today. From buttons to banners to breadcrumbs, these foundational components are required to be accessible, flexible, and performant across a wide variety of scenarios. Back in 2023, the number of components on certain pages began to explode. This led to several performance-r

Implementation
Alex Kladov

Finding Bugs (opens in a new tab)

FINDING BUGS Sep 19, 2026 Are generative (randomized) tests significantly more effective than example-based unit-tests at discovering bugs? There’s an interesting discussion about this on lobste.rs. One argument in favor of unit tests is, paraphrasing > My generic fuzzer wasn’t able to find this tricky bug in Rust regex crate. To me, it seems that

Implementation
NVIDIA Physical AI· Max Bickley

How to Use AI Agents to Prepare 3D Scenes for Simulation (opens in a new tab)

Agentic AI workflows can be used to prepare and validate digital twins for physical AI systems. Agents can inspect 3D scenes, author simulation-relevant data in... Agentic AI workflows can be used to prepare and validate digital twins for physical AI systems. Agents can inspect 3D scenes, author simulation-relevant data in OpenUSD, add physics prop

Implementation
GitHub Engineering· Erik Kristensen

How we make AI coding more cost efficient without sacrificing task quality (opens in a new tab)

Output quality is important when working with AI coding agents, but true efficiency comes from getting work done quickly, efficiently, and with the right context. That’s why token count of individual interactions alone isn’t a meaningful measure of efficiency. The goal shouldn’t be to use fewer tokens, but to tap into the right amount of context to

Implementation
NVIDIA Physical AI· Yan Chang

How to Train a Cross-Embodiment Robot Navigation Policy with AI Agents (opens in a new tab)

Navigation enables a robot to turn perception and motion into purposeful autonomy. Unlike locomotion, which produces stable movement, navigation must be used to... Navigation enables a robot to turn perception and motion into purposeful autonomy. Unlike locomotion, which produces stable movement, navigation must be used to continuously localize the

Implementation
NVIDIA Physical AI· Saeed Babamohamadi

Post-Train NVIDIA Cosmos 3 Edge for On-Device Robot Control (opens in a new tab)

Robots need policies that can adapt to their sensors, environments, and tasks while running on onboard computing hardware. World models offer a foundation for... Robots need policies that can adapt to their sensors, environments, and tasks while running on onboard computing hardware. World models offer a foundation for learning physical interaction

Architecture
NVIDIA Physical AI· Cristiana Dinea

Developing Healthcare Robotics with GPU-Native Medical Physics Simulation (opens in a new tab)

Unlike autonomous driving or industrial robotics, healthcare robotics can’t rely on internet-scale data collection or unlimited real-world experimentation.... Unlike autonomous driving or industrial robotics, healthcare robotics can’t rely on internet-scale data collection or unlimited real-world experimentation. Every demonstration requires specia

Research
Berkeley AI Research

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction (opens in a new tab)

Overview of ABBEL compared to traditional recursive summarization. Beliefs replace the full interaction history as the agent’s working context, and belief grading improves performance by supervising the contents of each belief state.. As task horizons grow, LLM contexts can’t scale forever. Self-summarization enables concise, interpretable contexts

Research
Berkeley AI Research

Gradient-based Planning for World Models at Longer Horizons (opens in a new tab)

GRASP is a new gradient-based planner for learned dynamics (a “world model”) that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity directly to the state iterates for exploration, and (3) reshaping gradients so actions get clean signals while we

Research
Berkeley AI Research

Information-Driven Design of Imaging Systems (opens in a new tab)

An encoder (optical system) maps objects to noiseless images, which noise corrupts into measurements. Our information estimator uses only these noisy measurements and a noise model to quantify how well measurements distinguish objects. Many imaging systems produce measurements that humans never see or cannot interpret directly. Your smartphone proc