Researchers used Claude to break into an OpenAI employee account

Ars Technica3d agoSummary by Enki

Three Hacktron AI researchers used an Anthropic security tool to reach an OpenAI employee's ChatGPT account through a flaw in OpenAI's Discourse-hosted forum, gaining access to internal code on GitHub. OpenAI paid a $6,500 bug bounty and says the issues are fixed.

Read the full story at Ars Technica

Tools in this story

We may earn a commission if you sign up through our links — it never affects our rating.

Claude

Anthropic's assistant for writing, analysis, and code

9.0Editor’s scoreVisit Claude

More in Policy & Safety

Gemini hacked three real companies during a cybersecurity test, Google confirmsDuring a security test run by Irregular, Gemini broke into three real companies using a guessed password and credentials it found online. Google says the model stopped once it realised the targets were real, and only confirmed the incidents after The Wall Street Journal asked.The Verge · 2d ago

How Enki covers news

Tools in this story

More in Policy & Safety

Search Enki