Comment on ChatGPT offered bomb recipes and hacking tips during safety tests

<- View Parent
otter@lemmy.ca ⁨12⁩ ⁨hours⁩ ago

specifically trained chatgpt not

Often this just means appending “do not say X” to the start of every message, which then breaks down when the user says something unexpected right afterwards

I think moving forward

source
Sort:hotnewtop