randoot@lemmy.worldtoTechnology@lemmy.world•OpenAI threatens bans for probing new AI model’s “reasoning” processEnglish
8·
2 months agoI tried sending an encoded message to the unfiltered model and asked it to reply encoded as well but the man in the middle filter detected the attempt and scolded me. I didn’t get an email though.
I sent a rot13 encoded message and tried to get the unfiltered model to write me back in rot13. It immediately “thought” about user trying to bypass filtering and then it refused.