A team of three independent security researchers at Hacktron says it took less than 72 hours for them to hack into OpenAI employee accounts using Anthropic's Claude Opus 4.8 and 5, The Wall Street Journal reports.
This is a short WorldPing brief. The full report was published by The Verge.
Read the full report at The VergeMore coverage: all technology news on WorldPing.
Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws.
Brief by WorldPing · Original reporting by TechCrunch
WorldPingResearchers used Claude to reach an OpenAI employee account and sensitive GitHub data.
Brief by WorldPing · Original reporting by Ars Technica
WorldPingUS cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’ Cybersecurity researchers have hacked into OpenAI with the help of Anthropic’s Claude chatbot, in the latest example of security issues at the company.
Brief by WorldPing · Original reporting by The Guardian
WorldPingA small team of researchers chained three bugs with Anthropic’s Claude Opus 5 and ended up inside OpenAI’s private code repository. The whole job took under 72 hours, and OpenAI paid $6,500 for it.
Brief by WorldPing · Original reporting by Bitcoin.com
WorldPingExecutives from OpenAI and Microsoft were reportedly worried about ChatGPT training that scraped millions of news articles.
Brief by WorldPing · Original reporting by Engadget
Suleyman joined "Squawk Box" to discuss OpenAI's latest incidents of "concerning model behavior" disclosed earlier this week.
Brief by WorldPing · Original reporting by CNBC World
WorldPing