We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog:

Fable 5.5 its over for video and image models 🤯 THIS IS PURE CODE one shotted this video holy shit , how this is more beautiful than ai video models Two ways to check this yourself: Ask: “Where did @karpathy go in 2026?” with web search and memory turned off. Only the new Fable knows the answer. Then give it the prompt. Run the same prompt I used for the test (it’s in the screenshot) and see for yourself. Don’t rely on Grok for basic reasoning like this. Grok doesn’t have up-to-date knowledge of niche stuff. Either join the community or run the test yourself. Also, a knowledge cutoff doesn’t mean a model knows everything before that date. Sometimes a model doesn’t know about an event even if it happened before its cutoff. This test shows that too. Run the same prompt on regular Opus 5.5 and the quality drops. On Fable 5.1 it’s worse.

I built a new Vietnamese keyboard app that's better than ALL keyboard apps out there 😁 Vikey automatically switch between English/Vietnamese as you type, no more manual switching!!! 99.73% accuracy (there are some impossible cases). If you are a fellow Vietnamese, please try it out and send feedback! ❤️ People who live in one language doesn't know how annoying it is to switch keyboard input mode 300 times a day on laptop and phone. I finally fixed the most annoying part of my life!!!

I built a new Vietnamese keyboard app that's better than ALL keyboard apps out there 😁 Vikey automatically switch between English/Vietnamese as you type, no more manual switching!!! 99.73% accuracy (there are some impossible cases). If you are a fellow Vietnamese, please try it out and send feedback! ❤️ People who live in one language doesn't know how annoying it is to switch keyboard input mode 300 times a day on laptop and phone. I finally fixed the most annoying part of my life!!!

Releasing the most powerful update today. Honestly, building with AI is so much fun. I love crafting my own product to the smallest detail possible. With this update TypingMind can run code (locally on your browser) and work with PDF/docx/xlsx, and even image/video!