Six lines of work

An agent reads a model's tensors, forms a hypothesis and patches safetensors directly. Tensor-Slayer made 44 targeted edits to Qwen-0.6B.

Sycophancy is a straight line in a small model's hidden states. Subtracting it took Qwen3-0.6B from 12.5% to 53.8% on pressure prompts.

RL and distillation on 0.6B–4B models. Claude diagnosed a 0.8B model's tool-call failures and wrote LoRA fixes: 42% → 75% strict accuracy.

An agent drives an iPhone over USB from Linux, no Mac needed. A signed Android client keeps a running agent in your pocket.

The Codex desktop app on Linux (57★), a kernel that schedules agent workers, and a terminal that draws the session as a tree of light.

Generative media where the model writes an editable score and a deterministic engine renders sound, or a million points of light.