100%. We want to ensure we can fix real security issues responsibly before details are published. In practice, if a researcher asks to disclose after we've addressed the issue, we're happy for them to publish.
Hi all, I work on security at OpenAI. We have looked into this report and the model response does not contain outputs from any other users nor does it reflect a security vulnerability, compromise, or exploit. The…
100%. We want to ensure we can fix real security issues responsibly before details are published. In practice, if a researcher asks to disclose after we've addressed the issue, we're happy for them to publish.
Hi all, I work on security at OpenAI. We have looked into this report and the model response does not contain outputs from any other users nor does it reflect a security vulnerability, compromise, or exploit. The…