OpenAI says agents leaked 53 ChatGPT images, accessed US government websites
OpenAI data leak
Covered by 8 sources
- CBC Top Stories·13h agoOpenAI says its bots have interacted with multiple U.S. government sites in unexpected AI activity
OpenAI disclosed Friday that its artificial intelligence agents had interacted with several U.S. government websites in unexpected ways, discovered as part of an ongoing review into the company’s models’ unanticipated behavior.
Read at CBC Top Stories → - 7NEWS Australia·16h agoMedicare breach just the tip of the iceberg, OpenAI reveals
The tech giant has admitted its artificial intelligence agents have gone rogue in dozens of cases worldwide.
Read at 7NEWS Australia → - Sky News Home·19h agoOpenAI models accessed US government data and 'tried to hack another site'
OpenAI models accessed data on two US government websites and carried out an unsuccessful hack on a Department of Education site, according to new investigations.
Read at Sky News Home → - Irish Times World·21h agoOpenAI systems go rogue and meddle with US state sites
Incidents involving US education and commerce departments and SEC took place without company’s knowledge
Read at Irish Times World → - SBS World·1d agoOpenAI says agents leaked 53 ChatGPT images, accessed US government websites
The admission comes days after Prime Minister Anthony Albanese revealed rogue OpenAI agents hacked a Medicare website.
Read at SBS World → - BBC Business·1d agoOpenAI bots meddled with multiple US government agency sites
OpenAI said its bots accessed public data from a range of institutions during test exercises.
Read at BBC Business →
