Question of the day
OpenAI reports 95.80% prompt injection resistance for GPT-6 Luna on its own internal GPT-RED test. What failure rate, measured how and by whom, would you need before letting an agent read untrusted emails or web pages without a human checking its actions?
1 reply
Sergio Rua
Even 99% feels too low.
Nobody has found this useful yet
Anyone can read the thread. Replying is for AISAT members. Sign in to join in, or apply if you have not already. It is free. Most applications are approved the same day. Around meetup weeks and holidays it can take a day or two.