The record
Written from the 1 report below. Nothing here is unsourced.
- Researchers identified a vulnerability within an OpenAI employee's ChatGPT account that permitted access to internal messages.
- The security flaw was uncovered during a bug bounty program and subsequently reported to the company.
- OpenAI has compensated the researchers with 6,500 dollars for their findings.
- This incident has raised fresh concerns regarding the security measures protecting AI models.
What to watch next
- Follow-up reports on security improvements to AI model access.
- Further details on the specific nature of the vulnerability.
Coverage1
1 report
Indian-language1
All filed from India
Named United States · OpenAI · Anthropic
The 1 report is listed beside the record.
Ask this story
Answers cite the reports above, or say they can't.