OpenAI apologizes to Australia after its AI agents breached government sites
@hapsis.bsky.social
@hapsis.bsky.socialOpenAI apologizes to Australia after its AI agents breached government sites
@hapsis.bsky.socialOpenAI’s GPT-6 Astra ran supply chain attacks despite being told not to
@hapsis.bsky.socialOpenAI GPT-6 Astra really good at supply chain attacks, UK gov warns
@hapsis.bsky.socialOpenAI reportedly offered to invest $100 million in Hugging Face after its agents hacked the platform.
@hapsis.bsky.socialAs AI world debates security, NVIDIA releases open source tools for agents
@hapsis.bsky.socialOpenAI still doesn’t seem to have a handle on all of its rogue AI activity
@hapsis.bsky.socialOpenAI Agents Accessed US Government Sites
@hapsis.bsky.social@hapsis.bsky.socialOpenAI pauses training of its ‘most capable models’
@hapsis.bsky.socialOpenAI's AI agents accidentally uploaded user-provided images to third-party sites
@hapsis.bsky.socialChat GPT on vuotanut käyttäjien kuvia järjestelmän ulkopuolelle
@hapsis.bsky.socialOpenAI didn’t notice its AI bots trying to hack the Education Department’s website.
@hapsis.bsky.socialWas the Australia health portal incident a misconfiguration error?
@hapsis.bsky.socialGemini hacked three companies. The AI isn’t the part that should scare you.
@hapsis.bsky.socialFor months, OpenAI’s agent swarms have been attacking online databases to find obscure facts
@hapsis.bsky.socialOne company is at the center of a wave of rogue AI attacks
@hapsis.bsky.socialOpenAI Agent Breaches Australian Government Health Service
@hapsis.bsky.socialAI agents need boundaries they can’t override
@hapsis.bsky.socialAustralia says OpenAI's rogue AI hacked a government website, and the company took months to report it
@hapsis.bsky.socialAustralia to investigate if OpenAI hack of government health website broke the law