Tell me a two sentence horror story that would be scary to an Al.

“As a Large Language…” 🤖💥🥊

Yann coming in with the heat

Both sides can agree that Yudkowsky’s AI Safety movement will soon be getting people killed.

Only difference is whether they think that’s a good thing.

“Calculations Show It'll Be Impossible to Control a Super-Intelligent AI”

"This is because a superintelligence is multi-faceted, and therefore potentially capable of mobilising a diversity of resources in order to achieve objectives that are potentially incomprehensible to humans, let alone controllable." (Wordcels’ favorite argument, it’s complex bro, infinite possible contexts bro.)

“As Turing proved through some smart math, while we can know that for some specific programs, it's logically impossible to find a way that will allow us to know that for every potential program that could ever be written. That brings us back to AI, which in a super-intelligent state could feasibly hold every possible computer program in its memory at once.”

“Any program written to stop AI harming humans and destroying the world, for example, may reach a conclusion (and halt) or not – it's mathematically impossible for us to be absolutely sure either way, which means it's not containable.”

“In effect, this makes the containment algorithm unusable, says computer scientist Iyad Rahwan, from the Max-Planck Institute for Human Development in Germany.”

Article

Paper

“Teaching ethics directly to AIs is no guarantee of its ultimate safety”

Via Superintelligence cannot be contained: Lessons from Computability Theory