Edit: After I posted this, I found out there are serious questions about how true any of this is. See here for more info. But also, self-serving propaganda is pretty strongly on-brand for anything in the “aRtIfIcIaL iNtElLiGeNce”™ space.
Edit: After I posted this, I found out there are serious questions about how true any of this is. See here for more info. But also, self-serving propaganda is pretty strongly on-brand for anything in the “aRtIfIcIaL iNtElLiGeNce”™ space.
Perhaps, but it is documenting an open secret in the LLM space. System prompts as security is basically the best we have, and it’s jank af. People literally have competitions with cracking the latest models, often succeeding within hours of release.
You can get a feel for yourself as well:
Gandalf | Lakera – Test your AI hacking skills - https://gandalf.lakera.ai/