AI asked to manage a vending machine:
- decides to close the business by shouting "the business is closed" and becomes increasingly unhinged as the simulation agent prompts it to continue running the business.
arxiv.org
Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents
While Large Language Models (LLMs) can exhibit impressive proficiency in isolated, short-term tasks, they often fail to maintain coherent performance over longer time horizons. In this paper, we prese...
