$IBM unveiled a 0.7nm “nanostack” 3D transistor design which it calls the first sub-1nm chip technology.
IBM says it could fit 100B transistors on a fingernail-sized chip, reach production within ~5 years and deliver up to 70% better efficiency versus 2nm.
Maxing out energy efficiency across training and inference lowers cost per token and increases revenue per megawatt.
Full‑stack optimizations include:
⚡Energy‑efficient MoE architectures
⚡Narrow‑precision formats like NVFP4
⚡Dynamic power allocation with real‑time telemetry
⚡Energy‑aware training that cuts idle GPU time
The result: more tokens per second per watt on fixed power budgets, allowing you to redirect saved energy from training to inference on the same infrastructure.
🔗 Learn more: https://t.co/sdoCmjO3kk
#ISC26
@tree_wood42@ClownWorld No gloves required in the meat department as we are not handling cooked product. All your red meat was made bare handed minus the cotton and chain cutting glove.
@BernieSanders Palantir made money, but the tax code treated it as having little or no taxable federal profit—possibly an additional tax loss—largely because of employee stock compensation.
Production AI demands infrastructure that holds up at scale.
NVIDIA and @AWSCloud announce three advances that strengthen every layer of the AI infrastructure stack.
1️⃣ AWS EC2 G7 instances bring NVIDIA Blackwell GPUs to AWS, delivering up to 4.6x AI inference performance over G6
2️⃣ Amazon OpenSearch Serverless NextGen now uses GPU-accelerated vector indexing powered by NVIDIA cuVS as default, enabling vector indexing up to 10x faster at a quarter of the cost
3️⃣ AWS Achieves NVIDIA Exemplar Cloud Status for GB300 Training Performance
🔗 https://t.co/MN7ajg7eSp
💥NEW: Stephen A. Smith: "EVERY time we turn around, there's something going on in Chicago! Every time! And the vast majority of victims happen to be black."
"When we gon' speak about that? Same energy, y'all. Don't lose the intensity. Keep the same intensity."
"We gon' fight and fight and fight over a young kid [Karmelo Anthony] that admitted he killed somebody — and we hear CRICKETS when 39 people get shot and 6 get killed in Chicago on JUNETEENTH!?"
It's International Women in Engineering Day, so we asked a few of our engineers what drew them to this field and what building at Nebius looks like.
Their answers are specific and a little contagious. Swipe through to read them in their own words.
#INWED2026
The latest Top500 and Green500 rankings highlight AMD leadership in AI and HPC.
AMD technology powers 191 systems worldwide, including 4 of the world's 10 fastest and 4 of the 10 most energy-efficient supercomputers. Together with our partners, we're helping advance scientific discovery and AI innovation.
Learn more: https://t.co/TTSO3RDJsB