arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.07153cs.CY
收藏

迈向AGI安全与治理的最佳实践:专家意见调查

Towards best practices in AGI safety and governance: A survey of expert opinion

Jonas Schuett, Noemi Dreksler, Markus Anderljung, David McCaffary, Lennart Heim, Emma Bluemke, Ben Garfinkel

AI总结:

本研究通过专家调查,发现专家普遍认同AGI实验室应采取的50项安全与治理措施,为制定最佳实践和标准提供了基础。

摘要:

包括OpenAI、Google DeepMind和Anthropic在内的多家领先AI公司,都明确将构建人工通用智能(AGI)作为目标——即在广泛认知任务上达到或超越人类表现的AI系统。在追求这一目标的过程中,他们可能会开发和部署带来特别重大风险的AI系统。尽管他们已经采取了一些措施来缓解这些风险,但最佳实践尚未形成。为了支持最佳实践的识别,我们向来自AGI实验室、学术界和公民社会的92位领先专家发送了调查问卷,并收到了51份回复。参与者被问及他们对50项关于AGI实验室应如何行动的陈述的同意程度。我们的主要发现是,参与者平均而言同意所有陈述。许多陈述获得了极高的同意度。例如,98%的受访者表示有些同意或强烈同意AGI实验室应进行部署前风险评估、危险能力评估、第三方模型审计、模型使用的安全限制以及红队测试。最终,我们的陈述清单可能为制定AGI实验室的最佳实践、标准和法规提供有用的基础。

英文摘要:

A number of leading AI companies, including OpenAI, Google DeepMind, and Anthropic, have the stated goal of building artificial general intelligence (AGI) - AI systems that achieve or exceed human performance across a wide range of cognitive tasks. In pursuing this goal, they may develop and deploy AI systems that pose particularly significant risks. While they have already taken some measures to mitigate these risks, best practices have not yet emerged. To support the identification of best practices, we sent a survey to 92 leading experts from AGI labs, academia, and civil society and received 51 responses. Participants were asked how much they agreed with 50 statements about what AGI labs should do. Our main finding is that participants, on average, agreed with all of them. Many statements received extremely high levels of agreement. For example, 98% of respondents somewhat or strongly agreed that AGI labs should conduct pre-deployment risk assessments, dangerous capabilities evaluations, third-party model audits, safety restrictions on model usage, and red teaming. Ultimately, our list of statements may serve as a helpful foundation for efforts to develop best practices, standards, and regulations for AGI labs.

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。

↑