Muve to the beat.
Muve the conversation.
Muve mountains.
Today @eurosky.social announces mu.social, a new microblogging app to experiment with the future of social! 🪩💖
Eurosky Social
Gemma 4 now runs 2x faster with MTP GGUFs! Run locally on just 6GB RAM. ⚡️
MTP enables Google Gemma 4 run ~1.4–2.2× faster with no accuracy loss.
Gemma 4 12B MTP can run at 162 t/s vs. 52 t/s without MTP. 31B reaches 101 t/s.
GGUFs + Guide: unsloth.ai/docs/models/...
Can the new DiffusionGemma model help fix broken OCR?
In theory, denoising tokens in parallel could work better for OCR correction since context is seen upfront?
Pointed it at 19th-century newspaper OCR. It corrected better than the autoregressive baseline — at ~8x the speed.
Pi agent spotted in Apple's WWDC session on local AI with MLX www.youtube.com/watch?v=wykP... @mariozechner.at
Things I really dislike about Fable:
1. Anthropic collects my prompt history, stores it, and does whatever they want with it for 30 days. No opt-out
2. They can nerf their most expensive model without telling me, billing me the same amount, wasting my time. Whenever they want
Finally a safe space for AI and agentic engineering here?
