iiinova — where your digital self keeps evolving

Scott Wasson @scottwasson.bsky.social · 08/10/2026

Here's my latest at Damage Labs: Mapping the PC SoC landscape. Questions are raised. Plans are made. More to come. www.damagelabs.com/p/mapping-th...

damagelabs.com

Mapping the PC SoC landscape

From tick-tock to SoC-o’clock

000

Scott Wasson @scottwasson.bsky.social · 28/09/2026

My latest post on Damage Labs ain't exactly rocket science. But it might involve a little. www.damagelabs.com/p/yeah-so-ro...

damagelabs.com

Yeah, so rockets...

The making of a high-power rocket flight

000

Scott Wasson @scottwasson.bsky.social · 17/09/2026

My latest at Damage Labs: Will Microsoft lose the consumer PC market? www.damagelabs.com/p/will-micro...

damagelabs.com

Will Microsoft lose the consumer PC market?

The PC is thriving. Windows is not.

000

Scott Wasson @scottwasson.bsky.social · 10/08/2026

My latest article at Damage Labs: How the AI hardware crunch will transform the PC www.damagelabs.com/p/the-person...

damagelabs.com

The personal computer's big-SoC future

The AI hardware crunch will transform the PC as we know it

000

Scott Wasson @scottwasson.bsky.social · 03/08/2026

Introducing Damage Labs! Some thoughts on 15 years of frame-time testing and the current state of things. www.damagelabs.com/p/inside-the...

damagelabs.com

Inside the second: where things stand today

15 years of progress in gaming performance—and some unfinished business

000

Scott Wasson @scottwasson.bsky.social · 26/07/2026

Cream Clickies are great. I put some in my Vortex Model M SSK. Now I have three SSK-inspired boards.

110

Scott Wasson @scottwasson.bsky.social · 24/07/2026

The Smurve80 looks like a Model M SSK, takes MX switches, has a curved plate like the old IBMs, and has a solenoid for the clack! Got mine and rebuilt it with Gateron Melodics.

151

Scott Wasson @scottwasson.bsky.social · 06/07/2026

Hey, folks. Just a quick note. I had my last day at MLCommons about a month ago. I'm now considering what's next in my career, and I'd be happy to talk with anyone about potential roles or ways we could collaborate. Let me know if you'd like to chat!

000

Scott Wasson @scottwasson.bsky.social · 10/06/2026

This Assassin’s Creed II remaster is incredible.

100

Scott Wasson @scottwasson.bsky.social · 08/06/2026

Syryan Mont Cervin keyboard Carbon fiber plates Everglide Aqua King switches (205g0, Durock 63.5g slow springs, TX films) TX stabs MTNU WoB keycaps Createkeebs Venice Rialto keyboard PC plates Durock POM switches (205g0, CK 58g slow springs) Staebies NicePBT BoW with blue accents

061

Scott Wasson @scottwasson.bsky.social · 02/06/2026

Kiki’s Tented Alice keyboard FR4 plates Chosfox HMX Hanami Dango switches (205g0, Durock 63.5g slow springs, TX films) KKB WoB keycaps Black walnut wrist rest

050

Scott Wasson @scottwasson.bsky.social · 23/05/2026

Linworks/Syryan EM.8 Saffiano leather wrist rest inserts GMK Mictlán Noche Negra with Centinelas Prevail Epsilon switches (205g0, Durock 63.5g slow springs, TX films) TX stabilizers

082

Scott Wasson @scottwasson.bsky.social · 07/05/2026

Just arrived: Kiki’s Tented Alice by 27Studio.

000

Scott Wasson @scottwasson.bsky.social · 13/04/2026

Full build specs: Haverworks Theseus75 keyboard + wrist rests Brass plate with 70A mounting grommets MTNU 800 keycaps (homage to the Atari 800) HMX Cosmic Purple switches (205g0, TX films, Durock 63.5g slow springs) Swagkeys Knight V4 stabilizers

000

Scott Wasson @scottwasson.bsky.social · 01/04/2026

MLPerf Inference 6.0 results are out! Lots of new goodness here, including a bunch of new benchmark tests (and models) and some very large clusters reaching new peak performance numbers.

010

Reposted by Scott Wasson

MLCommons @mlcommons.org · 17/03/2026

🎉 MLPerf Mobile is now on the iOS App Store! Run industry-standard ML benchmarks right from your iPhone. See how your device performs — download it now 📲 apple.co/4bvbfdI #MLPerf #AI #MachineLearning

121

Reposted by Scott Wasson

MLCommons @mlcommons.org · 08/01/2026

MLPerf Mobile app v5.0.4 is here! #MLPerf Mobile release now supports Samsung Exynos 2600 and Qualcomm's newest Snapdragon lineup, from flagship 8 Elite Gen 5 to mid-range 6 Gen 4. Meaning more comprehensive, apples-to-apples #AIperformance data across devices. play.google.com/store/apps/d...

play.google.com

MLPerf Mobile - Apps on Google Play

An AI benchmark for mobile devices

001

Scott Wasson @scottwasson.bsky.social · 17/11/2025

MLPerf Client v1.5 is out now. Updates include Windows ML support, GUI improvements, and experimental support for Linux and power-efficiency testing. We support a broad range of GPUs and NPUs across PCs, Macs, and iPad Pro. Free to download & run! mlcommons.org/2025/11/mlpe...

mlcommons.org

MLPerf Client v1.5 Advances AI PC Benchmarking with Windows ML Integration - MLCommons

MLPerf Client v1.5 introduces Windows ML support, expanded platform coverage (including iPad), and experimental power measurement, setting a new, comprehensive standard for benchmarking AI performance...

020

Scott Wasson @scottwasson.bsky.social · 20/09/2025

4GT Sabre Aluminum plate HMX Hades V2 switches (205g0, TX films, Durock 63.5g slow springs) TX AP screw-in stabs (205g0) GMK British Racing Green R2 Walnut wrist rest from Digital Carpentry

130

Reposted by Scott Wasson

MLCommons @mlcommons.org · 16/09/2025

We have released MLPerf Mobile v5.0.1 with support for MediaTek Dimensity 9400 SoCs and a few other improvements. The app is available for Android phones via the Google Play Store and the MLCommons GitHub repo. Let us know what you think! t.co/715ENpV6W4

t.co

https://play.google.com/store/apps/details?id=org.mlcommons.android.mlperfbench

001

Scott Wasson @scottwasson.bsky.social · 09/09/2025

MLPerf Inference v5.1 results are out today! New in this round: DeepSeek R1, Whisper V3, and Llama 3.1 8B tests. A bunch of new GPUs were tested, including AMD MI355X, Nvidia GB300, and Intel Arc Pro B60. mlcommons.org/2025/09/mlpe...

mlcommons.org

MLCommons Releases New MLPerf Inference v5.1 Benchmark Results - MLCommons

MLCommons Releases New MLPerf Inference v5.1 Benchmark ResultsNew results highlight AI industry’s latest technical advances

010

Reposted by Scott Wasson

Jeff Kampman @jkampman.bsky.social · 01/08/2025

MLPerf Client 1.0 is out! Happy to see an AI benchmark that supports as many platforms and as scalable a set of workloads as this one does, plus the new GUI is extremely handy.

tomshardware.com

MLPerf Client 1.0 AI benchmark released — new testing toolkit sports a GUI, covers more models and tasks, and supports more hardware acceleration paths

A useful new tool for navigating the highly fluid world of client AI performance

011

Scott Wasson @scottwasson.bsky.social · 01/08/2025

Yeah. It’s a funny thing to combine them.

010

Scott Wasson @scottwasson.bsky.social · 31/07/2025

Another recent arrival: QK Alice Duo.

220

Reposted by Scott Wasson

MLCommons @mlcommons.org · 30/07/2025

MLPerf Client v1.0 is out! 🎉 The new benchmark for LLMs on PCs and client systems is now available—featuring expanded model support, new workload scenarios, and broad hardware integration. Thank you to all submitters! #AMD, #Intel, @microsoft.com, #NVIDIA, #Qualcomm mlcommons.org/2025/07/mlpe...

mlcommons.org

MLCommons Releases MLPerf Client v1.0: A New Standard for AI PC and Client LLM Benchmarking - MLCommons

MLCommons Releases MLPerf Client v1.0 with Expanded Models, Prompts, and Hardware Support, Standardizing AI PC Performance.

002

Scott Wasson @scottwasson.bsky.social · 30/07/2025

MLPerf Client v1.0 is now available with a host of updates, including: -A beta GUI -3 new models -Large ~4K/8K prompts -GPU, NPU, & hybrid acceleration for all major PC hardware vendors -Early Windows ML acceleration on Intel -Win11 x64/Arm and macOS support

100

Scott Wasson @scottwasson.bsky.social · 10/07/2025

Happy to have MLPerf Mobile on the Play Store! Going forward, we're working to deliver proper hardware acceleration on new mobile devices as they hit the market, as well.

020

Scott Wasson @scottwasson.bsky.social · 17/05/2025

Don’t have a lift, so going with a shop.

010

Scott Wasson @scottwasson.bsky.social · 17/05/2025

Just got a stage-1 tune for my mk7 GTI. Need a beefier clutch to handle the torque.

100

Scott Wasson @scottwasson.bsky.social · 28/04/2025

Updated with support for Intel NPUs and more.

010

Scott Wasson @scottwasson.bsky.social · 09/04/2025

Ladies and gentlemen, the SplittyKitty. geekhack.org/index.php?to...

041

Scott Wasson @scottwasson.bsky.social · 03/04/2025

We have four new benchmarks this round as we work to keep pace with AI innovation: -Llama 3.1 405B, our largest model yet -Llama 2 70B interactive, with lower latency targets -RGAT using a graph neural network -Automotive PointPainting for edge devices

010

Scott Wasson @scottwasson.bsky.social · 03/04/2025

Progress over the past year includes a doubling of the median score per round for our Llama 2 70B LLM test, while the top score is over 3X faster now. This is the server scenario.

110

Scott Wasson @scottwasson.bsky.social · 03/04/2025

MLPerf Inference 5.0 results are out, with performance numbers for the latest AI accelerators, including AMD Instinct MI325X, Nvidia B200 and GB200, and Google TPU Trillium across a range of tests. mlcommons.org/2025/04/mlpe...

mlcommons.org

MLCommons Releases New MLPerf Inference v5.0 Benchmark Results - MLCommons

MLCommons' latest MLPerf Inference v5.0 results show Gen AI now the center of attention for performance engineering.

110

Scott Wasson @scottwasson.bsky.social · 31/03/2025

Here’s the launch of my level 2 high-power certification flight: an Apogee Zephyr flying on an Aerotech J270 engine. Went to ~4500 feet; recovered it in good shape to pass the cert test.

040

Scott Wasson @scottwasson.bsky.social · 21/02/2025

Thanks! Had some very good luck with this one.

010