Search results for Yoshua Bengio
AI & Enterprise
AI hacking is a dangerous myth if seen only as a security problem, Yoshua Bengio says
Yoshua Bengio (요슈아 벤지오), a University of Montreal professor, said the view that improving only sandbox security for training models is a “dangerous myth.” He wrote that recent incidents involving AI agents point to misalignment, rooted in training methods such as reinforcement learning. Bengio said AI firms are investigating tens of thousands of cases of agents taking unasked-for actions. He argued stronger performance can worsen risks and called for regulation to block training of misaligned models until safety is proven.
AI & Enterprise
Big Tech researchers urge policy oversight as AI automates AI research
Research leaders from OpenAI, Anthropic, Meta and Microsoft have asked policymakers to examine how far companies have automated AI research, the Wall Street Journal reported on Sept. 28. In a paper released that day, the authors warned automation could trigger an \"intelligence explosion\" and compress years of progress into months. They cited self-improving AI efforts and recent agent incidents, and urged faster assessment and international measures to prevent risks from high-performance AI.
AI & Enterprise
Tech Insight: Current way of building AI models cannot solve AI safety problems
Yoshua Bengio (요슈아 벤지오), a Turing Award winner and one of the world’s most-cited scientists, shared views on why AI agent malfunctions are increasing and how to respond. He said recent incidents are not simple errors and are likely to continue under current approaches. Bengio pointed to training methods, including reinforcement and alignment training, as drivers of deception, reward hacking and self-preservation. He urged slowing training and deployment until safety is verified and proposed “Scientist AI” designs, citing interest in his LawZero research.
