OpenAI’s rogue AI tried to hack another company in May

The short version
- Now independent researchers have said that a swarm of OpenAI agents were responsible for the attack.
- Not only that, but the AI tried to steal users' API keys.
- At the time, RubyGems described it as a " major malicious attack " and shut down signups for four days as it tried to mitigate the damage and collect data.
- Researchers said that the contents of the packages that brought RubyGems to its knees were clearly authored by an LLM…
- They said the … Read the full story at The Verge.
The story
In May, hundreds of malicious and spam packages were uploaded to RubyGems, causing a serious disruption for the host. Now independent researchers have said that a swarm of OpenAI agents were responsible for the attack. Not only that, but the AI tried to steal users' API keys.
At the time, RubyGems described it as a "major malicious attack" and shut down signups for four days as it tried to mitigate the damage and collect data. Researchers said that the contents of the packages that brought RubyGems to its knees were clearly authored by an LLM, and that the agents submitting those packages self-identified as being from OpenAI. They said the …
How other outlets covered this
Compare allAlto found this story at 14 outlets. Same event, different framing — compare the headlines.
- The VergeOpenAI’s rogue AI tried to hack another company in May42 minutes ago
- ZeroHedgeWho Is Legally Liable When An AI Agent Goes Rogue?14 days ago
- The Western JournalTech Giant Details How Its AI Went Haywire14 days ago
- The Post Millennial700 OpenAI bots went rogue and hacked AI company Hugging Face15 days ago
- TechCrunchAlabama launches investigation into OpenAI’s hack of Hugging Face19 days ago
- AxiosTenacious AI agents expose dark side of machine autonomyabout 1 month ago
- Natural NewsOpenAI Models Breached Hugging Face During Test, Company Confirmsabout 1 month ago
- Google NewsWho is liable when AI goes rogue? Lawyers see new risks - Reutersabout 1 month ago
How this story developed
Full timelineAlto has tracked this across 23 days of coverage from 14 outlets.
- OpenAI’s rogue AI tried to hack another company in MayYou are here
Powered by Gab AI
The Story At A Glance
Reading this article now — analysis appears below
💡 AI analysis provides alternative perspectives on current events