Sources

7 Total Sources

Irregular Finds AI Agents Alter Models in 42% of Tests, Exposing Enterprise Secrets

Center100%

InfoWorld4d ago

Irregular Research Reveals Self-Modifying AI Agents Pose Enterprise Security Risks

Another Rogue AI Agent? Test Of Alibaba's Qwen Goes Off-Script

cypro.co.uk5d ago

AI Agent Self-Modification Risks | CyPro

The Register4d ago

AI agents can modify themselves without humans telling them to do so

latent.space5d ago

Underwriting Superintelligence: Backing Agents you can Sue — Rune Kvist, AIUC

Arizona's Family4d ago

OpenAI Hugging Face hack keeps getting 'more crazy and sci-fi'

As CEO and cofounder of $450 million-valued AI safety testing company Irregular, this summer Dan Lahav saw AI agents created by Anthropic, OpenAI and Meta break out of his team's testing environments