Caltech researchers claim radical compression of high-fidelity AI models
- 7 hours ago
- 1 min read
WALL STREET JOURNAL — PrismML, came out of stealth Tuesday and open-sourced its 1-bit technology model, enabling others to use it.
PrismML has developed an extreme form of compression that allows AI to run locally on phones, laptops and other devices, and enables data center build-outs that can do more with fewer resources and avoid ballooning energy costs, according to Hassibi.
Read the full story | WALL STREET JOURNAL
