不要害怕收割者:反驳Bostrom的超级智能论点
Don't Fear the Reaper: Refuting Bostrom's Superintelligence Argument
摘要:
近年来,杰出的知识分子对人工智能的后果提出了伦理问题。一个担忧是,一个自主智能体可能会修改自己,成为“超级智能”,并在极其有效地追求不明确的目标时,摧毁整个人类。本文认为,并拒绝这种结果的可能性。我们认为,这种情况下依赖于代理的能力,迅速提高其能力,通过自我修改预测其环境。使用贝叶斯模型的推理代理,我们表明,有重要的限制,代理如何可以通过自我修改单独提高其预测能力。我们的结论是,对这种人工智能结果的担忧是错误的,最好是针对围绕数据访问和存储的政策问题。
英文摘要:
In recent years prominent intellectuals have raised ethical concerns about the consequences of artificial intelligence. One concern is that an autonomous agent might modify itself to become "superintelligent" and, in supremely effective pursuit of poorly specified goals, destroy all of humanity. This paper considers and rejects the possibility of this outcome. We argue that this scenario depends on an agent's ability to rapidly improve its ability to predict its environment through self-modification. Using a Bayesian model of a reasoning agent, we show that there are important limitations to how an agent may improve its predictive ability through self-modification alone. We conclude that concern about this artificial intelligence outcome is misplaced and better directed at policy questions around data access and storage.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。