More evidence of move to local models.
— Robert Scoble (@Scobleizer) 2 avril 2026
This one running on the claw. On a laptop. https://t.co/oEGqhlQ9JQ
More evidence of move to local models. This one running on the claw. On a laptop.
COMPUTING
-
Local AI Models Running on Laptop Hardware
By
–
-
Chip Design Requires Predicting the Future Four Years Ahead
By
–
The AI market moves fast, but chips take years to build. In his @TEDTalks, @RodrigoLiang shares why chip design is part science, part vision, part predicting the future 4 years from now.
— SambaNova (@SambaNovaAI) 2 avril 2026
Watch his full talk 👇
https://t.co/19qDsfiHlk pic.twitter.com/qOQSpLdFjiThe AI market moves fast, but chips take years to build. In his @TEDTalks, @RodrigoLiang shares why chip design is part science, part vision, part predicting the future 4 years from now. Watch his full talk 👇 bit.ly/41G3vAO
→ View original post on X — @sambanovaai, 2026-04-02 21:05 UTC
-
Gemma 4 streaming from Mac Studio to iPhone via Tailscale
By
–
Pro tip – hook your PC and Phone with Tailscale and enjoy fast and private inference on the go.
— Georgi Gerganov (@ggerganov) 2 avril 2026
Here is Gemma 4, hosted on Mac Studio, streaming to my iPhone.
No 3rd party apps. Same WebUI experience everywhere. pic.twitter.com/tkfaFDvzvbPro tip – hook your PC and Phone with Tailscale and enjoy fast and private inference on the go. Here is Gemma 4, hosted on Mac Studio, streaming to my iPhone. No 3rd party apps. Same WebUI experience everywhere.
→ View original post on X — @huggingface, 2026-04-02 20:38 UTC
-
Datacenter Downtime Risks Infrastructure Reliability Issues
By
–
Oh, sure. But what I said is accurate. And taking offline one datacenter causes problems even in a perfect world.
-
Robotic Claw System with Autonomous Feeding Capability
By
–
And you can feed it to your claw! (feed at the bottom) 🙂
-
Oracle Layoffs Boost NVIDIA as Datacenter Investments Reshape AI Market
By
–
Oracle this week laid off tens of thousands to pay for its datacenters. Now getting blown up. Who wins? NVIDIA. What a f***ed up world we are living in.
-
Google Gemma 4 31B achieves 2.7X faster performance on RTX
By
–
.@GoogleGemma 4 31B is up to 2.7X faster on RTX using llama.cpp. Thanks to @ggerganov for working with us to make this model fast.
→ View original post on X — @huggingface, 2026-04-02 19:30 UTC
-
Legacy-Bench: AI Agents Benchmark for COBOL, Fortran, Assembly
By
–
No major benchmark is designed for COBOL, Fortran, or Assembly – the languages powering trillions in transactions and infrastructure that must be modernized or risk catastrophic failure. We built Legacy-Bench to measure frontier agents on the code the world actually runs on.
→ View original post on X — @nathanlands, 2026-04-02 19:18 UTC
-
GoodAI Swarm Robotics: Indoor Navigation Test with Drone
By
–
GoodAI Swarm Robotics: Indoor Navigation Test
— Marek Rosa | European🇪🇺 | South African🇿🇦 (@marek_rosa) 2 avril 2026
We scanned our offices using the lidar mounted on a drone, then post-processed the data to create a suitable simulator environment.
The drone flies in the environment, creating a global map and a navigation graph. It then combines… pic.twitter.com/T14SySTglXGoodAI Swarm Robotics: Indoor Navigation Test We scanned our offices using the lidar mounted on a drone, then post-processed the data to create a suitable simulator environment. The drone flies in the environment, creating a global map and a navigation graph. It then combines long range navigation (using the graph depicted with red nodes), and short range navigation. Short range navigation follows the global trajectory (chasing the yellow ball) and can react to changing conditions (obstacle avoidance). @GoodAIdev
→ View original post on X — @marek_rosa, 2026-04-02 19:11 UTC
-
Overall Architecture Overview and Implementation Guide
By
–
Here you go (for the overall architecture):