Priorities in AGI governance research | Jade Leung | EA Global: SF 22
EA Talks
00:00
Ensure That Things Go Well
Dali: I take a very existential risk focus perspective in this talk and in my work. When I say ensuring things go well, I basically mean avoiding these kinds of high stakes risks. If you imagine that we don't navigate this period well, then we'll be locked into a world with misaligned and unsafe AGI. Dali: The two threat models that loom the largest are accidentally being deployed or misuse by actors. And then there could be a whole bunch of other problems for large AI systems depending on how you think stuff's going to go down.
Transcript
Play full episode
