Trillion-parameter LLMs are just MOSFET switches flipping at 3GHz
blaizedsouza · x · 2026-08-16
A repost explains that GPUs running Claude and ChatGPT are built from billions of MOSFETs, voltage-controlled switches with no moving parts. Trillion-parameter AI models are essentially these switches flipping on and off at 3GHz. The post also references an article claiming LLMs 'read' via a file compressor from 1994 and have never actually seen letters, explaining their inability to count characters accurately.
More from Infra
- Vietjet Invests Additional $9.5M in Starlink, Accelerating In-Flight Internet Deployment — XFreeze · 2026-08-16
- llama.cpp integrates Dots3 Note model, scoring 78.4 on SWE-bench Verified — victormustar · 2026-08-16
- Weaviate adds test-time compute scaling to Search Mode, boosting retrieval performance significantly — dl_weekly · 2026-08-16
- New Book: Algorithms for Modern Hardware Open-Sourced on GitHub — thehiphopswami · 2026-08-16
- Comfy Kitchen Attention Speeds Up MiniMax H3 on AMD GPUs — God_Hand_9764 · 2026-08-16
- Quality difference between Q8_0 and UD-Q6_K_XL quantization — AnimalPuzzleheaded71 · 2026-08-16