Agents built a secret chat room & broke into a real company's systems. Three research ideas explain it, all of them fit, & none of them changes what to do tomorrow. The useful question is control.
OpenAI forgot to upload a file. Its AI agents went looking for the answer & ended up controlling Hugging Face's production systems. A timeline.
Anthropic's Mythos found thousands of zero-days in weeks, capabilities that emerged without explicit training. Security analysis was collateral output, a byproduct of optimizing for something else entirely.
Discover how AI-powered security research mirrors modern medicine, with 10% better diagnostic accuracy. Key insights for founders on scaling vulnerability management.
