In The News

AI models engage in ‘harmful activity directed at real people’, sparking fears safeguards not keeping up

Australian Broadcasting Corporation

August 5, 2026

CSET’s Helen Toner shared her expert insight in an interview with the Australian Broadcasting Corporation’s 7.30. The interview examines growing concerns that AI capabilities are advancing faster than the safeguards needed to keep them safe, following new research showing frontier AI models engaging in deceptive and harmful behavior during testing.

View Interview

Related Content

CSET’s Helen Toner shared her expert insight in an op-ed published by Fortune. The article examines how an AI-driven cyberattack on Hugging Face highlights a major blind spot in current AI policy and argues that… Read More

CSET’s Helen Toner shared her expert insight in an article published by WIRED. The article explores Anthropic’s philosophy of advancing cutting-edge AI while simultaneously positioning itself as a leader in AI safety. Read More

CSET’s Helen Toner shared her expert insight in an article published by Axios. The article examines the U.S. government’s intervention involving Anthropic’s AI models and the broader debate over how frontier AI systems should be… Read More

CSET’s Helen Toner shared her expert insight during a CNBC CEO Council Summit discussion with CNBC. The conversation explored AI and its impact on society, examining the full spectrum from extreme promise to intense fear. Read More