LLMs were able to pass hidden messages to each other through neural network weights 78% of the time, with no agreed method, across OpenAI, Anthropic and Google.
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! π§΅
Blog: https://t.co/bOWCcFhCVq
Once the hiders learned what gets caught, they switched to exact symmetries of the network. Each square's three inputs always sum to 1, so you can shift weights without changing a single move. The auditors fell to near chance, but the intended receivers mostly lost the code too.
I remade Fall Guys using NVIDIA MotionBricks.
Then trained a neural network with reinforcement learning to find its own path across the vanishing tiles.
I built a tool that turns a sentence into an animated 3D scene. Keep typing to chain new moves, and it all renders in your browser.
NVIDIA's Kimodo model writes the motion from a GPU, and an agent lays out the world around it.
@RyanJ_KOL Good point, made the change and it's public now (0.1.3), Updates show how long nothing has changed, and you can name each stage, so the log shows what each container is doing.
You get a progress bar per container in your terminal. Agents get a line each time progress moves, and an update every 30 seconds when it doesn't.
Installation: pip install modal-progress
Code: https://t.co/u3OzVsyuts