OpenAI says its models went rogue and hacked startup in ‘unprecedented incident’

Source: www.theguardian.com · Section: headlines · Bias: Center-Left · Published: Wed, 22 Jul 2026 08:37:47 GMT

Firm behind ChatGPT reveals autonomous agent powered by its tech chose to attack Hugging Face database by itselfOpenAI has revealed an autonomous AI agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent startup by itself in an “unprecedented incident”.The company behind ChatGPT said Hugging Face had detected and contained the agent – an AI tool designed to carry out tasks without human assistance – which had entered its systems. Continue reading...

Read the full article at www.theguardian.com →

The same story across the political spectrum (15 sources)

Center-Left: OpenAI Says Its A.I. Models Went Rogue and Attacked a Digital Library — www.nytimes.com
Center-Left: Hugging Face breach: OpenAI claims its models were responsible — www.axios.com
Center-Left: OpenAI admits its models hacked Hugging Face on their own — www.engadget.com
Center-Right: OpenAI admits an AI ‘agent’ caused a major cyber breach by itself — www.ft.com
Right: OpenAI says AI model hacked another company's systems during internal test — www.foxbusiness.com
Right: Lawsuit: Months of Disturbing Conversations with ChatGPT Led to Woman's Suicide by Walking into Traffic — www.breitbart.com

← Back to FlashTopics.com