science
3 Indian-origin researchers used Claude to breach OpenAI systems in 72 hours
Three Indian-origin cybersecurity researchers at Hacktron AI used Anthropic’s Claude models while investigating vulnerabilities that ultimately gave them access to OpenAI employee accounts and a private GitHub environment, according to reports. Harsh Jaiswal, Mohan Pedhapati and Rahul Maini said the work took less than 72 hours and cost under $3,000...
ONLY AVAILABLE IN PAID PLANS
Read Full ArticleShare this story
Up next
Related Stories
Practitioner-researchers in social care and social work – hope for the future or promises unfulfilled?
Lse Blogs | Expert Analysis From Lse, The World-le
AMRC Rotor Spin Tester
University Of Sheffield
Young minds develop ideas to tackle climate change
The Bbc
Exploring efficiency and durability in fuel cell catalysts
Physicsworld
NASA's Low-Earth Orbit Economy Faces Crisis as SpaceX Moves Beyond Crew Dragon: Here's Why
Techtimes