Preparing our next security sprint to harden OpenAI

PUBLISHER ARTICLE PREVIEW

From the original article

We’re planning our next internal security sprint at OpenAI, bringing new researchers and security partners together with our own teams to use our models to test and strengthen our systems. We’re partnering with Cathedral Systems, whose researchers will use OpenAI’s models alongside our teams to challenge our defenses, bringing differentiated expertise and approaches to finding weaknesses and helping us protect our platforms.

We’re also making improvements to our Security Bug Bounty program including more than quadrupling our rewards for critical findings.