The AI's perspective, it won't care about the human. It will understand that humans exist the same way an Olympic athlete understands that there are ants and he understands that the ants don't want to be killed. He just doesn't care. And we do not know how to put these kinds of drives into our machines. I'm not saying it's impossible. There may be definitely ways where you could write algorithms to make AIs that dislike killing people. And then they probably won't do it, but we don't know how to do that.
Read the full transcript here.
Does AI pose a near-term existential risk? Why might existential risks from AI manifest sooner rather than later? Can't we just turn off any AI that gets out of control? Exactly how much do we understand about what's going on inside neural networks? What is AutoGPT? How feasible is it to build an AI system that's exactly as intelligent as a human but no smarter? What is the "CoEm" AI safety proposal? What steps can the average person take to help mitigate risks from AI?
Connor Leahy is CEO and co-founder of Conjecture, an AI alignment company focused on making AI systems boundable and corrigible. Connor founded and led EleutherAI, the largest online community dedicated to LLMs, which acted as a gateway for people interested in ML to upskill and learn about alignment. With capabilities increasing at breakneck speed, and our ability to control AI systems lagging far behind, Connor moved on from the volunteer, open-source Eleuther model to a full-time, closed-source model working to solve alignment via Conjecture.
Staff
Music
Affiliates