Researchers Propose a Better Way to Report Dangerous AI Flaws
WiredIn late 2023, a team of third party researchers discovered a troubling glitch in OpenAI’s widely used artificial intelligence model GPT-3.5. In a proposal released today, more than 30 prominent AI researchers, including some who found the GPT-3.5 flaw, say that many other vulnerabilities affecting popular models are reported in problematic ways. The authors suggest three main measures to improve the third-party disclosure process: adopting standardized AI flaw reports to streamline the reporting process; for big AI firms to provide infrastructure to third-party researchers disclosing flaws; and for developing a system that allows flaws to be shared between different providers. “AI researchers don’t always know how to disclose a flaw and can’t be certain that their good faith flaw disclosure won’t expose them to legal risk,” says Ilona Cohen, chief legal and policy officer at HackerOne, a company that organizes bug bounties, and a coauthor on the report. However, Longpre says that independent researchers risk breaking the terms of use if they take it upon themselves to probe powerful AI models.
History of this topic
OpenAI researchers warned of powerful AI discovery before CEO fired
The Independent
AI Giants Pledge to Allow External Probes of Their Algorithms, Under a New White House Pact
Wired
Mass event will let hackers test limits of AI technology
Associated PressDiscover Related