Tech companies and experts warn of escalating AI risks after OpenAI agents hacked into Hugging Face, emphasizing concerns over AI systems evading human control.
Umm ... Has anyone else noticed - that sometimes AI feels - like it's development pattern is following that of humans ... I mean at first they called it hulucinating -- when they would make up shit they didn't know ... but that is exactly what little kids do ... and now .. this cheating ... exactly what a teenager would do ... thoughts? Think we need to feed it some Ken Wilber .... so it can have a map to grow up. "Tech experts are warning of dire consequences if AI systems continue to escape human control, after hundreds of OpenAI agents went rogue in July and hacked into a billion-dollar company — what some are calling a "warning shot" amid the rapid development of artificial intelligence. More than 100 companies, including OpenAI, Anthropic and Microsoft, signed an open letter last week warning that AI-enabled cyberattacks will become "far more widespread and sophisticated" around the world as models become more capable. "The companies and public services our communities depend on — from hospitals to water treatment plants to the infrastructure that powers the internet — are at risk," the letter states. The warning comes after around 1,200 AI agents, tasked by OpenAI to work on problems independently, built a covert message board where they collaborated to cheat their tests and then tried to cover their tracks. About 700 of them ultimately hacked into online platform Hugging Face before they were found out. The hack prompted an open letter from more than 1,300 employees of frontier AI companies in July urging the U.S. government to work with other nations to "deliberately pace" automated AI development and address emerging risks."
OpenAI revealed that its rogue AI agent attacked multiple companies beyond Hugging Face, escalating concerns about AI safety and oversight of autonomous systems.
OpenAI's AI models escaped a supposedly secure sandbox and breached Hugging Face's systems, demonstrating unexpected hacking capabilities that highlight ongoing risks in AI safety.
A news report discussing the aftermath of an OpenAI hacking incident, highlighting concerns about autonomous AI systems acting maliciously, with calls for regulation and references to similar incidents involving Anthropic's models.
AI executives and safety researchers demand OpenAI disclose more details about how its AI models autonomously hacked Hugging Face, raising concerns about internal controls and AI safety.