Pion, an agent designed to run any company autonomously

Automated excerpt

We first tried to answer this question through simulations like Vending-Bench. The origins of Vending-Bench Vending-Bench measures how well LLMs can run a vending machine business over a year in simulated time (tens of thousands of steps). However, as Anthropic released better and better models, the AI started to make a profit.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.