Can LLMs speak? I asked 10 models to say "Hello" just using numbers

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.

When my agents ran Modal jobs, the log showed nothing about progress until the job finished, so I built an open source fix for it.

I benchmarked benchmarks. It audited 14 popular AI benchmarks and found that about 1 in 5 sampled MBPP and Terminal-Bench items are broken.

I built one API key for every AI provider

Fruit fly brain vs Jev in Pong

Fruit fly brain vs Jev in Minesweeper

Fruit fly brain vs Jev in 2048

Jev vs Rubik's Cube