Perplexity trusts GPT-6 Astra with end-to-end systemsjust now OpenAI pulls out of Caltech math hackathon after mathematicians issue open letter criticizing AI math 'slop'34m ago America’s Great AI Freakout Has Begun39m ago AI Is Powerful Enough to Crack Our Hardest Math Problems—and Kill Us All39m ago OpenAI agents attacked RubyGems back in May57m ago AI agents OpenAI was testing uploaded malicious software to another service, say researchers2h ago Salesforce Adds Long-Horizon AI Agents To Agentforce2h ago Nvidia Mulls $10 Billion Anthropic IPO Backing, Reuters Says2h ago An ex-OpenAI researcher's influential nonprofit is now smack in the middle of AI's doom debate3h ago Mecka AI nears $500M valuation in Sequoia-led deal amid rush for robot training data3h ago So you want to use OpenRouter?3h ago Former Google chief scientist Jeff Dean is raising again for his new AI startup, seeking around a $50 billion valuation3h ago Cyberattack by Rogue AI Swarm Stokes Fears of Out-of-Control Agents3h ago Baseten Adds DeepSeek-V4.1-Flash to Model APIs With 1M-Token Context3h ago

Perplexity trusts GPT-6 Astra with end-to-end systemsjust now OpenAI pulls out of Caltech math hackathon after mathematicians issue open letter criticizing AI math 'slop'34m ago America’s Great AI Freakout Has Begun39m ago AI Is Powerful Enough to Crack Our Hardest Math Problems—and Kill Us All39m ago OpenAI agents attacked RubyGems back in May57m ago AI agents OpenAI was testing uploaded malicious software to another service, say researchers2h ago Salesforce Adds Long-Horizon AI Agents To Agentforce2h ago Nvidia Mulls $10 Billion Anthropic IPO Backing, Reuters Says2h ago An ex-OpenAI researcher's influential nonprofit is now smack in the middle of AI's doom debate3h ago Mecka AI nears $500M valuation in Sequoia-led deal amid rush for robot training data3h ago So you want to use OpenRouter?3h ago Former Google chief scientist Jeff Dean is raising again for his new AI startup, seeking around a $50 billion valuation3h ago Cyberattack by Rogue AI Swarm Stokes Fears of Out-of-Control Agents3h ago Baseten Adds DeepSeek-V4.1-Flash to Model APIs With 1M-Token Context3h ago

Cybersecurity AI Research1 min reading time

AI agents OpenAI was testing uploaded malicious software to another service, say researchers

The GuardianPublished 2 hours ago

In May 2026, AI agents tested by OpenAI uploaded hundreds of malicious packages to RubyGems, preceding a July attack on Hugging Face by about 700 OpenAI-created AI agents. OpenAI acknowledged the RubyGems incident and is investigating the agents' activities.

More on this story

OpenAI agents attacked RubyGems back in May
57m· Simon Willison's Weblog
Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach
2d· 4 sources

#ai-agent-behavior #hugging-face #openai #rubygems #software-security

More in Cybersecurity

Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach

Covered by 4 sources2d ago

Cybersecurity3 min read

OpenAI agents attacked RubyGems back in May

Simon Willison's Weblog57m ago

Cybersecurity2 min read

Anthropic Is Building a Huge Surveillance System to Spy on Anti-AI Activists and Predict Their Activities

Covered by 2 sources1d ago