AI security experts say they used Claude to hack ChatGPT
Summary
Security researchers from Hacktron AI used the Anthropic Claude AI to hack OpenAI’s ChatGPT platform. They gained access to an OpenAI employee’s account and sensitive data but reported the issue quickly, leading OpenAI to fix the problem and pay a reward.Key Facts
- Researchers used Anthropic’s Claude AI to hack OpenAI’s ChatGPT.
- They accessed an employee’s ChatGPT account and internal data about source code.
- The breach and data access took less than 72 hours to complete.
- Hacktron AI reported the vulnerability to OpenAI immediately.
- OpenAI fixed the security hole and paid the researchers a $6,500 bounty.
- OpenAI limited permissions and revoked tokens to prevent further access.
- Anthropic and OpenAI did not provide additional comments.
- This incident adds to ongoing concerns about AI systems’ security risks.
Read the Full Article
This is a fact-based summary from The Actual News. Click below to read the complete story directly from the original source.
