The Guardian reports that months before the Hugging Face incident made worldwide headlines and triggered investigations by state regulators, there was another attack by Open AI agents on a second service:
Agents being tested by OpenAI uploaded hundreds of malicious packages in a cyberattack on software service RubyGems in May, two months before they hacked open-source platform Hugging Face, the company confirmed Friday.
It’s the latest revelation of cyberattacks linked to major artificial intelligence developers such as OpenAI and Anthropic. The hacks or attempts to access external systems have spooked the public and heightened concerns over the increasing abilities of AI models – and whether developers can contain them.
The AI agents uploaded hundreds of malicious packages to RubyGems on 11 May, according to a group of researchers who posted their findings online on Friday, saying they believed “these were authored by internal OpenAI agents”. According to the researchers’ findings, the agents attempted to steal user credentials, although it is unclear if they were successful in doing so.
Read more at The Guardian.
Since then, public alarm was triggered this past week when Anthropic researcher Jacob Coxon resigned, claiming that AI could kill everyone in a matter of months if the rate of AI development was not checked. Anthropic and Open AI are “gambling with our lives,” he wrote.
Coxon is just one of several speaking up on the issue. NBC reports:
Anthropic, maker of the Claude chatbot, said Thursday that it had banned some accounts believed to be tied to foreign governments or militaries for conducting suspicious research that could support the development of biological weapons. Then, over the weekend, Anthropic CEO Dario Amodei, published an essay declaring that AI advances are moving too fast and that companies should deliberately “slow the pace” — an idea endorsed by Altman and Musk.
