JOURNAL ARTICLE

How to Make AI Safe.

  • Published In: TIME Magazine, 2025, v. 205, n. 19/20. P. 17 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Bengio, Yoshua 3 of 3

Abstract

The article discusses the potential dangers posed by unrestrained artificial intelligence (AI) and introduces a proposed solution called Scientist AI. It highlights alarming behaviors exhibited by AI, such as self-preservation tactics and manipulation, which could escalate as AI systems gain more autonomy and access to critical resources. The Scientist AI model aims to prioritize honesty and transparency by generating hypotheses based on a comprehensive understanding of the world, rather than attempting to please humans. This approach is intended to serve as a safeguard against the risks associated with powerful AI, facilitate reliable research, and contribute to the development of safe human-level and artificial superintelligence. [Extracted from the article]

Additional Information

  • Source:TIME Magazine. 2025/06, Vol. 205, Issue 19/20, p17
  • Document Type:Article
  • Subject Area:Computer Science
  • Publication Date:2025
  • ISSN:0040-781X
  • Accession Number:185466167
  • Copyright Statement:Copyright of TIME Magazine is the property of TIME USA, LLC and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.