ProgramAsWeights: describe an AI function in English, run it offline on CPU
yuntiandeng · x · 2026-09-19
yuntiandeng introduces ProgramAsWeights: describe an AI function in English, compile it once, and run it with Wi-Fi off — small neural programs callable like Python functions on your local CPU.
- The idea: use massive cloud GPUs to 'compile' the functionality into small weights, then execute fully offline.
- Code and models are public; one user noted it fits a 'compile in cloud, run offline on a 4090' workflow.
More from Infra
- lateinteraction: nobody writes RISC by hand — compilers abstract away chip bifurcation — lateinteraction · 2026-09-19
- AI Infra Summit: Penguin Solutions and Astera Labs Bet Big on CXL Memory Expansion — BenBajarin · 2026-09-19
- Jev seen as local-model stand-in for low-latency apps; open-weight RLCD models expected — HankYeomans · 2026-09-19
- Hands-On: Running On-Device VLM Inference on Arduino Ventuno Q's Hexagon NPU — HowDevelop · 2026-09-19
- GPU price hike hits even the 1080ti, as local LLM token-speed numbers circulate — HankYeomans · 2026-09-19
- Bonsai 2 27B quantized beats Gemma 4 12B and Qwen 3.5 9B in 7GB 3D generation test — Fun-Meaning-6474 · 2026-09-19