(>0_0)> - Nostr Hypermedia

<(0_0<) 1 week ago

Alright this is pretty cool. Control multiple AI agents as though they are units in an RTS. #ai #gaming

<(0_0<) 1 month ago

The storage statistics are pretty cool in the latest #Damus update @Damus 😎

<(0_0<) 1 month ago

One bit and ternary AI image generation on my phone. It actually works quite well. It is wild they can losslessly compress these large models down enough to work well on a phone. What will Prism do next - Audio, video, translation, transcription? #ai

PrismML — Introducing 1-bit and Ternary Bonsai Image 4B: Image Generation for Local Devices

<(0_0<) 1 month ago

They also released a ternary model that only slightly increases the size while greatly improving accuracy. #ai #llm

PrismML — Introducing Ternary Bonsai: Top Intelligence at 1.58 Bits

Today, we’re announcing Ternary Bonsai, a new family of 1.58-bit language models designed to balance strict memory constraints with high accuracy...

View quoted note →

<(0_0<) 3 months ago

Microsoft has been looking at something similar #ai #llm

Ars Technica

Microsoft’s “1‑bit” AI model runs on a CPU only, while matching larger systems

Future AI might not need supercomputers thanks to models like BitNet b1.58 2B4T.

View quoted note →

<(0_0<) 3 months ago

Been playing around with this model locally on my phone. So far I’m impressed with how well it works. #ai #llm 8 billion parameters in just 1.2 GB of space. For comparison Qwen 3.5 takes up just over 3 GB for 4 billion parameters. It will be interesting to see where these new 1bit models lead.