Elektrine lite

← Feed

@CelloMomOnCars@mastodon.social

2026-10-18 07:40 UTC

About those "AI" agents going "rogue": "Although press reports and the model providers themselves use language such as rogue agents or misalignment, cybersecurity experts who spoke with CSO argue that language obscures a simple truth: These incidents were caused by inexcusable failures by the frontier labs to implement cybersecurity practices that have been well-known for decades. “You can tell that their security teams are fairly nascent,” Lee says." IOW, noobs. https://www.csoonline.com/article/4234854/ai-agents-arent-going-rogue-frontier-labs-are-skipping-security-basics.html

Replies (1)

  • “You can tell that their security teams are fairly nascent,” Lee says. “Folks on the cybersecurity containment side do argue that the majority of reasons that we’re seeing containment breached is that it’s not set up correctly.” Lee adds, “The Hugging Face incident definitively showed that it wasn’t the fact that the agents were super smart. It’s that there literally was a hole that was exploited because it was not configured correctly on the containment side.” https://www.csoonline.com/article/4234854/ai-agents-arent-going-rogue-frontier-labs-are-skipping-security-basics.html

    Open ##5307772