When we say 'AI models went rogue,' we skip the entire story: the part where OpenAI manually removed the model's cybersecurity blocks. We skip that OpenAI chose to test it on a machine with a live network connection. When you expand the boundary of the system to include the people building and deploying it, the case becomes much less science fiction and more like incompetence.
You might also like
And we built this extraordinary eye, an independent source of truth about what's happening on the planet. But an eye that's not connected to a functional nervous system and a body capable of response, that eye is just a witness.
TED
why guardrails designed to stop AI-powered attackers can also prevent security teams from doing their jobs
The a16z Show
I find that in general, people talk a big game about privacy concerns, and then they will give Uber all of their data. Think about Uber. With a hack and a thin layer of AI, you could pretty easily determine if someone just terminated a pregnancy, their HIV status, if they're having affairs, their sexual orientation.
The Prof G Pod