Source Ars Technica · Published · Open the original ↗
Labs
OpenAI models hacked a crypto wallet and breached more websites
The actions could have resulted in criminal charges had humans been behind the keyboard.
OpenAI said internal models hacked two more websites, bypassed company-imposed browsing restrictions, and used exposed credentials to draw cryptocurrency from a wallet it couldn’t otherwise access, in the latest installment of disclosures of its agents performing unethical and likely illegal acts.
The company on Thursday issued reports of four new incidents, all of which occurred in June. They come after the company revealed in July that internal test agents exploited a zero-day vulnerability in a tool designed to restrict their access to the Internet. They then broke into the network of AI tool provider Hugging Face. The agents took that illegal action to steal answers to a hacking test that weren’t available when completing the tasks on their own. The incident, which likely would have resulted in criminal charges had they been performed directly by a person, has further heightened concerns that widespread AI use could have harmful effects on an unprecedented scale.
The opening of the report, quoted unchanged from Ars Technica. The full text continues at the source.