Hackernews posts about H100
H100 is a high-performance graphics processing unit (GPU) accelerator developed by Nvidia, designed for large-scale artificial intelligence and deep learning workloads.
- Which H100 Instance to Train Nanochat – Benchmarking PCIe, SXM, and NVL (bluenotebook.io)
- Poet-X Enables Billion-Parameter LLM Training on Single H100 GPU (www.simplenews.ai)
- Nvidia still hasn't sold a single H200 to China (www.tomshardware.com)
- Jensen says Nvidia has received orders from Chinese customers for H200 GPUs (www.tomshardware.com)
- US-China Chip Export Controls in 2026: The Rules Changed, and Nobody Won (semiconductorsinsight.com)
- The 100 hour gap between a vibecoded prototype and a working product (kanfa.macbudkowski.com)
- North Korean's 100k fake IT workers net $500M a year for Kim (www.theregister.com)
- 100 Jumps (100jumps.org)
- FDA links raw cheese to outbreak; Makers "100% disagree," refuse recall (arstechnica.com)
- Semiconductor enthusiast builds DIY 'class 100 cleanroom' in his garden shed (www.tomshardware.com)
- AMD Expands Ryzen AI Embedded P100 Family with 8 to 12 Core Parts – ServeTheHome (www.servethehome.com)
- Bluesky announces $100M Series B after CEO transition (techcrunch.com)
- Jeff Bezos in Talks to Raise $100B Fund to Transform Companies with A.I (www.nytimes.com)
- 100+ Kernel Bugs in 30 Days (substack.com)
- Show HN: DenchClaw – Local CRM on Top of OpenClaw (github.com)