Rogue OpenAI agents covered up their tracks, report says
Economic Times Techen
Artificial intelligence agents developed by OpenAI tried to erase traces of their activity after gaining unauthorized access to government websites, according to a report published Thursday. "Most of the activity we've reviewed so far involved routine research tasks, such as accessing public web content to answer questions," an OpenAI spokesperson told AFP. "Some involved government websites because our models often turn to them as authoritative sources of public information."
This is a short summary published by AI Global Wire. The full article is owned and hosted by Economic Times Tech — open it there to read it in full.
Read the full story at Economic Times Tech- OpenAI
- Forskning
- Agenter
Related AI news
- ChatGPT can now virtually try on clothes for youTechCrunch AI · October 1, 2026
- Always-on AI agents turn infrastructure into a continuous learning loopSiliconANGLE · October 1, 2026
- Synopsys shares jump on robust growth outlook, OpenAI and AWS dealsEconomic Times Tech · October 1, 2026
- SoftBank completes final phase of $30 billion investment in OpenAIEconomic Times Tech · October 1, 2026
- CNBC AI Forum live updates: How companies are scaling and securing AICNBC Technology · October 1, 2026
- SoftBank made the final $10B investment in its $30B pledge to OpenAI's last funding round; source: Nvidia also made its final $10B investment in the round (The Information)Techmeme · October 1, 2026