OpenAI engineers cut ChatGPT guest traffic to a few hundred Nvidia GPUs, with no new hardware deployed.

OpenAI inference cost reduction cut ChatGPT guest traffic from tens of thousands of Nvidia GPUs to just a couple hundred, using software optimization alone. Engineers achieved more than 50% savings ...
Tech Times

OpenAI Halves Inference Costs With Software Alone: GPUs Drop to Hundreds

OpenAI inference cost reduction cut ChatGPT guest traffic from tens of thousands of Nvidia GPUs to just a couple hundred, ...
Tech Times

Compile Once, Run Offline: New AI Method Matches 32B Models With a 23MB File

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2 ...

Waterloo's PAW compiles task specs into 23MB LoRA adapters a 600M-parameter model runs entirely offline.

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2, 2026, a system that compiles any natural-language task spec into a 23MB ...