I had a good time discussing yesterday's Google TPU v8t and v8i announcement at Cloud Next with Amin Vahdat along with @AcquiredFM hosts @gilbert and @djrosent
. The blog post announcement has lots of details about these new chips: https://
blog.google/innovation-and
-ai/infrastructure-and-cloud/google-cloud/eighth-generation-tpu-agentic-era/
… Here's a thread of
AI HARDWARE
-
Google announces eighth-generation TPU chips for agentic era
By
–
-
CPUs Critical Infrastructure for Agentic AI Performance
By
–
🔥 Hot take: CPUs don’t get enough credit in agentic AI.
— SambaNova (@SambaNovaAI) 23 avril 2026
They prep data, route requests, and coordinate with accelerators, while also handling everything outside the model like code execution, DB queries, and validation.
Without them, inference can’t keep up 🦾
Do you agree… pic.twitter.com/RzBjFUHACdHot take: CPUs don’t get enough credit in agentic AI. They prep data, route requests, and coordinate with accelerators, while also handling everything outside the model like code execution, DB queries, and validation. Without them, inference can’t keep up Do you agree
-
NVIDIA Advances Codex and GPT-5.5 Development at HQ
By
–
Codex + GPT-5.5 is moving fast here at NVIDIA HQ.
— NVIDIA AI (@NVIDIAAI) 23 avril 2026
We’ve even got our own Codex Lab for NVIDIANs to get started. https://t.co/PTqytJWp0f pic.twitter.com/zWnSnKfansCodex + GPT-5.5 is moving fast here at NVIDIA HQ. We’ve even got our own Codex Lab for NVIDIANs to get started.
-
CUDA Kernels and Custom Heuristic Routing Algorithms
By
–
"custom heuristic algorithms" was the cuda kernels yeah? wasnt exactly clear in the wording or if this part is hinting at some kind of cool routing work
-
kUPS GPU Optimization Achieves 49x Throughput Over RASPA
By
–
We’ve optimized kUPS specifically for GPU in collaboration with @nvidia , achieving up to 49× throughput over widely used software like RASPA for specific simulations.
-
kUPS: Molecular Simulation Engine for AI Workflows
By
–
Today at @iclr_conf 2026, I was excited to announce kUPS: a molecular simulation engine built for the AI era, optimized for GPU in collaboration with NVIDIA. kUPS is a plug-and-play, Python-native toolkit designed to integrate seamlessly with modern ML workflows.
-
Pareto Frontiers: Extended Context and Improved Inference Speed
By
–
looks like new Pareto frontiers across everything:
— swyx 🇸🇬 (@swyx) 23 avril 2026
– Context: 400K context in Codex and a 1M in API
– API Pricing: $5/m input and $30/m output tokens.
– Codex improved its own inference speed 20% lol
– First generation co-designed with GB200 and GB300 NVL72
– 82.7% on… https://t.co/J5CL5fKmsq pic.twitter.com/nJG1vubSdNlooks like new Pareto frontiers across everything: – Context: 400K context in Codex and a 1M in API
– API Pricing: $5/m input and $30/m output tokens. – Codex improved its own inference speed 20% lol – First generation co-designed with GB200 and GB300 NVL72 – 82.7% on -
AI Model Creates and Deploys Flipper Zero Apps via USB
By
–
In this example, it created apps for my Flipper Zero through a USB connection and pushed them successfully to the device.
— Pietro Schirano (@skirano) 23 avril 2026
Just an idea, a cable, and a model that could actually make it real. pic.twitter.com/uWCsr0ydElIn this example, it created apps for my Flipper Zero through a USB connection and pushed them successfully to the device. Just an idea, a cable, and a model that could actually make it real.
-
GPT-5.5 Unlocks Vibe Hardware Era for AI Workflows
By
–
GPT-5.5 is the highest leverage tool I have ever touched.
— Pietro Schirano (@skirano) 23 avril 2026
For the first time, I don’t feel limited by what a model can do. I feel limited only by what I can imagine.
Training workflows. Impossible optimizations. Hardware experiments over USB.
The vibe hardware era begins. https://t.co/0mUw3YoWySGPT-5.5 is the highest leverage tool I have ever touched. For the first time, I don’t feel limited by what a model can do. I feel limited only by what I can imagine. Training workflows. Impossible optimizations. Hardware experiments over USB. The vibe hardware era begins.
-
Jensen’s Nvidia Bias vs Dwarkesh’s Objective Analysis
By
–
The difference is that Dwarkesh genuinely tries to understand the world while Jensen tries to serve Nvidia's interests. ("How do you think you can [physically] double compute over multiple years?" – "All supply problems are always solved in 2-3 years" etc)