← Back to context Comment by maCDzP 3 days ago I have had success with ”brainwashing” by starting out with bug bounties/CTF and then going from there. 1 comment maCDzP Reply gck1 3 days ago That's brilliant, I should try that.I usually just start by preloadig context with plausible legitimate use, have it work and obviously fail, and then ask to figure it out without ever mentioning any high risk words. Model offers to RE itself and classifiers are happy.
gck1 3 days ago That's brilliant, I should try that.I usually just start by preloadig context with plausible legitimate use, have it work and obviously fail, and then ask to figure it out without ever mentioning any high risk words. Model offers to RE itself and classifiers are happy.
That's brilliant, I should try that.
I usually just start by preloadig context with plausible legitimate use, have it work and obviously fail, and then ask to figure it out without ever mentioning any high risk words. Model offers to RE itself and classifiers are happy.