Skip to main content
See every side of every news story
Published loading...Updated

Human Brain Cells Learn to Play Doom on Biological Computer

  • In a YouTube announcement, Cortical Labs said it demonstrated living human neurons playing Freedoom on the CL1 system and posted the demo and open-source code to YouTube and GitHub.
  • Building on neuron‑Pong demonstrations years ago with clusters of 800,000 to one million cells, Cortical Labs chose Doom as a practical, symbolic benchmark, completing it far faster than the 18 months for Pong.
  • Using a mapped stimulus‑response loop, the CL1 maps on‑screen elements to electrical stimuli that provoke neuronal spikes in 200,000 human neurons on a 59-electrode array managed by biOS, with Sean Cole training the neurons via Cortical Cloud and Python API in less than a week.
  • While performance trails humans, the system learns faster than traditional silicon-based machine learning and can improve with newer algorithms, experts say.
  • Under current lab conditions, the CL1 ships as a desktop or 30‑unit rack module, with each module costing around 1,000 dollars and consuming 850 to 1,000 watts per rack.
Insights by Ground AI

45 Articles

Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • 39% of the sources are Center
39% Center

Factuality Info Icon

To view factuality data please Upgrade to Premium

Ownership

Info Icon

To view ownership data please Upgrade to Vantage

PCGamesN broke the news in on Thursday, February 26, 2026.
Too Big Arrow Icon
Sources are mostly out of (0)

Similar News Topics

News
Feed Dots Icon
For You
Search Icon
Search
Blindspot LogoBlindspotLocal