Christos Tzamos @ChristosTzamos · 11 Mar 2026

3/4 Instead of using an external tool, the model executes the program directly via its transformer weights, producing an execution trace token by token and streaming results at more than 30k tokens/sec on a CPU. All computation is done autoregressively inside the transformer! https://t.co/HwNZq7Esgq

Open on X →