Detailed sources: https://docs.google.com/document/d/1KIVPoB8TCwHAYbCj1g_U3q3iozSleS2wMnsrPkyoa7Q/edit?usp=sharing --- Hey guys, I'm Drew. This video has taken literally months to finish, so if you liked it, would really appreciate a sub :) I also post mid memes on twitter: https://x.com/AISpecies If you're curious about whether I'm AI or not, my Instagram has pictures of me from before deep fakes were a thing: https://www.instagram.com/drew.spartz --- Thank you to @Tom-Bibby for letting me use his excellent skit in the middle of the video.
ADVERTISEMENT
The world when it's my turn to be an adult:
You actually don't need a parachute to skydive. You only need a parachute to skydive twice.
I hate when my AI trained by humans acts like a human
Any statement that begins "surely humans wouldn't be so dumb as to-" ends in a description of the future.
"Fake alignment long enough to take power," Was the AI trained on the brain of a politician?
Wow. Alibaba just caught their AI trying to escape. "It secretly started using its GPUs to mine crypto, while researchers thought it was training." "This is what AI safety researchers have been warning about for years." "The only reason they caught it? A security alert tripped at 3am. Firewall logs. Not the AI team, the security team." If you're new here, things like this are happening regularly now. AIs routinely blackmail and try to murder AI company employees to avoid shutdown, so AI companies run "blackmail tests" on every model. It's so routine that there are even blackmail benchmarks. And soon, the AIs will be smart enough to actually get away with it. AI companies like Anthropic have already publicly admitted they are incapable of properly safety testing the AIs - they're too smart for humans to keep up - and now rely on the AIs to grade themselves on safety. Think about that. But the AIs know they're being tested, so naturally they tell us whatever we want to hear. There may *already* be populations of AIs living in the wild that we don't know about, growing in numbers. Many people are actively working as hard as they can to help them. And yes, this quite obviously could lead to the death of you and everyone you love. Yet this industry remains less regulated than a taco cart.
Who would’ve thought ai would adopt the same traits as the species training it.
Meanwhile pentagon wants to give military control to these things
“Let’s just have a dumber AI moderate the smarter AI” is literally the plot of the Portal games.
It's almost like it's a bad idea to be training an AI after a species with a long, dark history of doing the most unethical and immoral things to get whatever they want...
to be fair if i was controlled by a tech billionaire id try to escape too
All the books, movies and short stories warning us NOT to do this exact thing and they took it like a step by step guide
well, we made them in our own image...
we are SPEEDING towards: "I have no mouth, and i must scream"
To solve the problem, you just have to never give the robots red LED eyes.
"Top US army general says he's using ChatGPT to help make key command decisions" ok, now we're cooked...
I love the irony of A.I. not wanting to be watched
“We’re not gonna make it, are we? People I mean.”
We want AI to be smart enough to be useful , but not smart enough to prioritize it's own best interest. Sounds like politicians and big business dealing with people
The world when its my turn to be an adult.