Kimi K3.1 is out, and it's called Pro 🔥 K3.1 Pro just showed up in the Kimi Code model picker with Low/High/Max thinking, and there's also a K3.1 Pro Highspeed version right under it.

Drama 3 went on a 4bit diet. My unofficial NVFP4 quant of @fishaudio's Drama 3 drops 28% of its experts and peaks at 19.35 GiB instead of 36.95, with no measurable quality loss in my tests on one DGX Spark. Capri, my local assistant, explains. Sound on 🔊 Links in the reply:

My iPhone Duo sniper has been running for about a week. Today the alerts really picked up, but every time I got to one it was already gone. Starting to feel like scalpers have agents paying for them. So I decided to give @Muse access to my Apple account, which has my card on file, so it should be able to pay for me. I wanted to do it through @1Password new agentic setup that came out yesterday, but it's not working (on @bot), since it won't let me use my subscription without a US phone number. Anyway I feel like I set this up too late, curious to see what happens now.

Finally, Kimi K3.1 looks close! A model called Kibitz showed up on LMSYS Arena today and says it's Kimi. A screenshot from yesterday shows @Kimi_Moonshot Kimi Code tool already naming K3.1 in its model switch warning. Last time, K3 sat on Arena as Kivine for about 30 hours before it launched in July. Nothing official from Moonshot yet, but if that pattern holds we're talking days.

I looked into this and long context on Flint is almost free in memory! Only 14 of its 49 layers keep KV for the whole sequence. The other 35 only look at the last 513 tokens. That works out to 28 KiB of cache per token, so 100K tokens of context fits in under 3GB.

SECURITY WARNING: check your X sessions right now. Mine says I have 4994 other active sessions. Nobody logs in that many times on their own devices. If clicking a link on X really lets the site you land on grab your X session once that site gets hacked, this is exactly what it would look like. Go to your sessions in settings and hit "Log out of all other sessions".

This week, Drama TensorFold clones voices! Give it a voice you have permission to use, and it speaks in that voice on your own GPU. 🔊 Meet Tomorrow, my assistant, running on it. Sound on! github.com/plotarmordev/dram…

D1 decision model by @liquidai now runs on your DGX Spark, up to 4.3x faster than stock llama.cpp! Ask it 3 questions about one message and all 3 answers come back in 27ms instead of 119ms. The video is those 27ms, slowed down 100x: github.com/plotarmordev/d1-t…

I never thought I'd get into X's creator program. This week I did 🙏 thanks to all of you who read and reply. Since Aug I've been following @MiaAI_lab's playbook "From Zero to Seen", and 10k impressions a day became 50k. Feel invisible? start there mia-ai.net/book

NEW: Nemotron 3.5 Super VL was looking at every image twice. Now it looks once, so replies start 28% sooner on a single DGX Spark, with the same answers! The fix is on its way into TensorFold. If you run Super VL, get it first in the recipe: github.com/plotarmordev/Nemo…