Skip to content
← Best of the week
AI Hardware

AI methods for hardware design and manufacturing this week

Design, verification, layout, simulation, firmware and manufacturing methods, often using AI, with lessons from practice.

Updated Nov 12, 2026. Read from 36 sources every four hours.

See the full ranked list Free account. No card.
  1. 1MethodWorth trying this weekFirst seen Nov 12, 2026

    Make a Robot Arm Feel Weightless with NVIDIA Holoscan 5

    Picture guiding a robot arm by hand while its motors supply just enough torque to support its weight and keep the robot upright. This simple interaction, a... Picture guiding a robot arm by hand while its motors supply just enough torque to support its…

  2. 2MethodWorth knowingFirst seen Nov 12, 2026

    1945 Packard V-1650 crankshaft drawing to modern GD&T

    A week ago I posted renders of the V-1650 Merlin crankshaft I modeled from the original Packard drawings. Several people asked whether I actually know GD&T. So I took the original 1945 drawing and redrew it to ASME Y14.5-2018. This is sheet 1 of 5. Some…

  3. 3MethodWorth knowingFirst seen Nov 12, 2026

    Catch Electronics Shock and Drop Failures Before Hardware Is Built

    Learn how guided virtual shock and drop analysis helps engineering teams identify reliability risks before physical testing, reduce qualification iterations, optimize packaging designs, and accelerate electronics product development. What you will learn…

  4. 4MethodWorth trying this weekFirst seen Nov 12, 2026

    From Human Demonstrations to Robot Training Data With RLWRLD | Cosmos Labs

    How do you turn a video of someone working into training data a robot can learn from? Join NVIDIA and RLWRLD for a walkthrough of a pipeline that connects human demonstrations to robot actions, visual observations, and task instructions. Follow the process…

  5. 5MethodWorth knowingFirst seen Nov 12, 2026

    Accelerating Reinforcement Learning Weight Refit with the Reshard Collective

    During reinforcement learning (RL) post-training, training trajectories are generated on the fly by running inference with the current policy model. For... During reinforcement learning (RL) post-training, training trajectories are generated on the fly by…

  6. 6MethodWorth knowingFirst seen Nov 12, 2026

    Intel and Altera expand collaboration to simplify sensor integration for physical AI

    Altera and Intel are collaborating to accelerate the development of intelligent systems across industries. Intel Corp. and Altera Corp. today said they are jointly developing flexible, real-time, sensor-bridge reference systems for edge and physical AI…

  7. 7MethodWorth knowingFirst seen Nov 12, 2026

    Running AV Reasoning Models Within Onboard Compute and Latency Limits

    Autonomous vehicle (AV) developers need reasoning models that can operate within the compute and latency constraints of an onboard system. Larger models provide... Autonomous vehicle (AV) developers need reasoning models that can operate within the compute…

  8. 8MethodWorth knowingFirst seen Nov 12, 2026

    Doubly twisted DPOT ganged programming

    Select and set one or both channels of a dual digipot with a twist of the wrist. Tandem potentiometers (i.e., pots that share a common control shaft) have been around for an extremely long time. That’s because they can be extremely handy. Adjusting the…

  9. 9MethodFirst seen Nov 12, 2026

    Sometimes 3d printing feels like torrenting real life objects. Saw this and thought to myself... ya no way Im paying $39 for a little…

    I use it for my magic trackpad

  10. 10MethodWorth knowingFirst seen Nov 12, 2026

    How to minimize Wi-Fi roaming interruptions for autonomous mobile robots

    Wi-Fi connectivity needs to be reliable for real-time mobile robot management. Source: Synaptics An autonomous mobile robot or AMR may cross dozens of Wi-Fi coverage zones during a single shift. Each transition creates a small but potentially consequential…

8 more ranked this week.

AI Hardware in Spezia ranks every find as it lands, today and this week, with filters by kind and by source, and you can ask Spezia whether each one is worth your time.

How it is ranked

  • Each item is judged for a hands-on hardware engineer (electrical, mechanical, semiconductor, embedded, robotics or manufacturing): how much it could speed up or improve real design, verification or build work this week, whether it is new, and whether there is a real product, part, project or result behind it.
  • How hot it is where it was found counts too: points, stars, upvotes, views and likes, each on its own scale.
  • A find picked up in several places at once ranks higher than one seen once.
  • Today fades an item by half its lift every two days. This week ranks on quality alone.
  • Nobody pays to be listed.

More on AI Hardware: what it does and what it reads.

More from AI Hardware

Other desks