#discourse

3 stories

#ai security #anthropic #claude #openai #technology #bug bounty #hacktron #heif heist #vulnerability #ai capabilities #chatgpt #codex

Security Researchers Hacked OpenAI Using Claude
Security researchers exploited a flaw in OpenAI's forum to take over employee ChatGPT accounts via Anthropic's Claude.
PCMAG · 1m
Claude hacked into OpenAI in bug bounty test
Security researchers used Anthropic's AI to break into OpenAI, exposing how accessible hacking tools have become.
TechCrunch · 2m
Hackers used Claude to break into OpenAI
Three researchers exploited an image processing flaw to access OpenAI's most sensitive code repository in under 72 hours.
The Verge · 1m · 5 views