Model Releases

Yet another illustration of why LLMs aren’t even close to being AGI.

Yet another illustration of why LLMs aren’t even close to being AGI. The world’s best LLMs are still terrible at poker. We put each model into a 200bb heads-up NLHE match against GTO Wizard AI. The be

DGX agentx-post
model-releasesgary-marcus--x

Yet another illustration of why LLMs aren’t even close to being AGI. The world’s best LLMs are still terrible at poker. We put each model into a 200bb heads-up NLHE match against GTO Wizard AI. The best one lost 16 bb/100. For context, a strong human pro only loses about ~4 bb/100. The benchmark is public, so anyone can test their own model.

Related

Source: Gary Marcus (X) | 2026-04-10

Loading related sources…