Cyber researchers broke into OpenAI using its key rival Anthropic’s software, highlighting vulnerabilities in the ChatGPT maker’s security as leading AI companies face mounting scrutiny over safety.
A small cyber security group gained access to an OpenAI employee’s ChatGPT account, which permitted them to read private software information and suggest changes.
The researchers had been given access to an Anthropic tool specifically designed for security professionals, and were paid for the work as part of a program to find vulnerabilities before they could be exploited by bad actors.
More in Technology
OpenAI and Microsoft knew they were starting a ‘doom loop’ for the web
September 18, 2026
FAA tees up $875M AI tool to help manage air traffic congestion
September 18, 2026
Virginia governor creates an AI task force and moves to restrain data centers
September 18, 2026
Disney’s first CTO is Character.AI’s former CEO
September 18, 2026
FCC lets Paramount sell 49.5% equity stake to Saudi Arabia, UAE, and Qatar
September 18, 2026
Finding the cells that put our brain to sleep
September 18, 2026
Latest News
World Series of Darts Finals: Schedule with Littler, Humphries, Price in action
September 18, 2026
Arteta: Dowman could go out on loan in future
September 18, 2026
Brentford score three in dominant win over Chelsea to continue unbeaten start
September 18, 2026
Littler overcomes lively crowd to beat Noppert at World Series of Darts Finals
September 18, 2026
Game over! Carvalho scores Brentford third to seal win over Chelsea
September 18, 2026
Wakefield through to first Super League semi-final with win over Leigh
September 18, 2026