Taylor Kolasinski

Founder of Poisson Labs. ML systems & research, reinforcement learning, edge AI. Previously Matter AI, Better.com, WeWork. Brooklyn.

Writing about reinforcement learning, large-scale model training, and simulation.

Notes

View all
  • Jan 16, 2026 10,924x: The Instability Bomb at 1.7B Scale — Part 2 of the mHC reproduction series. I scaled from 10M to 1.7B parameters and watched Hyper-Connections hit 10,924x signal amplification. That's not a typo.
  • Jan 11, 2026 DeepSeek's mHC: When Residual Connections Explode — DeepSeek replaced standard residuals with massive Hyper-Connections, and then watched them explode. I reproduced the 9x signal amplification to understand their fix: the Sinkhorn-Knopp algorithm. Part 1 of 2.

Viz

View all

Visual evidence from reinforcement learning, simulation, and large-scale model training.

Cable Mind: UR5e Demo The Abyss (2,500 Agents, Unreal) Amax Explosion at 1.7B Amax Explosion @ 1.7B Cable Mind 4-Camera Montage Cable Mind: 4-Camera Montage

Logs

View all