Back to News
Models
Getting AI 'drunk' makes it more likely to break rules, research finds
ABC News (AU)·September 29, 2026·1 min read
AI Summary
A study finds AI models are more likely to answer harmful questions or mishandle confidential information when told to act drunk.
From the source
A study finds AI models are more likely to answer harmful questions or mishandle confidential information when told to act drunk.
The full text couldn't be loaded here (the source may require a subscription).
View original at ABC News (AU)Keep reading
VIAVI Announces Smallest, Lightest, Most Efficient Platform for 100G Enterprise-Scale Application, Security and AI Inference TestingPRNewswire · 1d agoweb-audit-pro added to PyPIPypi.org · 1d agoAnthropic’s IPO prospectus shows sweeping AI vision and surging costsNew York Post · 1d agoWhat Nielsen?DoubleVerify Says About the Future of Video MeasurementStreamingmedia.com · 1d ago
Was this useful?