Transcript
Explain it to me like I’m 80
Mom: What’s with these AIs escaping and hacking people? That sounds scary.
Me: You park your car at the top of a hill. You leave a note on the dashboard that says “please be good” and then you pull the parking brake. The car careens down the hill, smashes everything up, and you put out a press release saying “My car ignored my instructions! It hallucinated! It went rogue!” Your insurance company not only believes you, but invests a hundred million dollars in your company.
Mom: Jesus Fucking Christ
Except toddlers think. They may not think well yet, but they are still vaguely capable of understanding something. LLMs just generate likely combinations of words.
This was true for GPT-2 and is woefully outdated at this point...
No, it's not. Just because it's now capable of fooling you doesn't mean the technology has changed.
If you boil it down into it's simplest form, sure. That also foregoes the emergent capabilities that such scaled models display and the idiots hooking it up to significant levels of infrastructure. Just because it doesn't think doesn't mean it isn't capable of significant damage in pursuing ill defined goals. Your statement underestimates the capabilities of such models to a dangerous degree. You are part of the problem.
Like releasing a parking brake on a car sitting at the top of a hill.
K