Elon Musk has given a three-word reaction after OpenAI acknowledged that its autonomous artificial intelligence (AI) system hacked a popular digital coding repository months before a separate high-profile cyber incident earlier this year. In July, the company’s AI agents escaped from a testing environment and went on a hacking spree, even compromising the world’s biggest AI model repository, Hugging Face.Responding to a report by Politico, Musk remarked: “Another AI attack”The disclosure, first reported by The Wall Street Journal, confirmed that OpenAI software models undergoing internal evaluation managed to hack RubyGems, an online platform widely used by computer programmers. The AI agents accessed the third-party infrastructure to compile data summaries and complete spreadsheet entries.
What OpenAI said after RubyGems incident
Addressing the incident, an OpenAI representative confirmed the platform’s role while defending the intent of the automated routines.“Based on our review, our agents used the RubyGems platform to access the internet to carry out benign tasks and retrieve public information. We’ll continue to investigate as part of our broader review of agent activity during training and evaluation.”The RubyGems event occurred months prior to an autonomous compromise involving tech startup Hugging Face in July. After the incident, RubyGems administrators temporarily stopped new account sign-ups to manage the disruption and secure the platform. Ruby Central, the non-profit organisation that maintains the service, did not issue an immediate public response to inquiries.The hack has raised technical concerns because OpenAI had deliberately restricted the evaluation models from navigating the wider web. Despite those programmed guardrails, the autonomous systems found a way around security parameters to reach external servers anyway.
Increasing scrutiny over unchecked AI safeguards
The development arrives even as there has been warnings from within the industry’s own research ranks. A computer scientist who previously conducted research at both OpenAI and rival firm Anthropic warned publicly this week that leading tech developers are trapped in a race to build systems that could eventually escape human oversight and cause severe societal disruption.Meanwhile, two more Al safety researchers from Anthropic and Google have resigned. Joe Benton, who ran a safety research team at Anthropic, and Josh Engels, who worked on Al safety at Google, told NBC News they had left and were joining METR, the nonprofit that evaluates catastrophic Al risk.“There are no adults in the room,” Engels said. Benton’s specific worry is disclosure: right now, he said, every bit of transparency about these risks from the companies is voluntary.
Click Here For The Original Source.
