I am trying to find some Alignment direction that could be interesting for me to learn and work on, I've already received a couple of answers but I want more opinions and I just get more motivation from the discussions/cooperation. 1. As I understand that almost any agent can be...
I have watched the Bankless interview with Eliezer Yudkowsky, and along with "Death with Dignity," they give the impression that Eliezer gave up. It's not the critique of Eliezer somehow. It's been a long hard way, and I appreciate what he has done and is doing. There is a place...
I am trying to find some Alignment direction that could be interesting for me to learn and work on, I've already received a couple of answers but I want more opinions and I just get more motivation from the discussions/cooperation.
1. As I understand that almost any agent can be modeled as an utility optimizer, but I am still suspicious about the concept. I am not sure that utility optimization is the most compressed representation of any agent, because an arbitrary utility function could be arbitrarily complex to encode, and maybe there is another model of this agent that is more compressed. Humans seem to be not explicit utility optimizers: Shard Theory. Can... (read 485 more words →)
I think at the moment when hoping for aliens is the best plan we really fucked up )))
Yeah, of course, I agree. But, as I said, I didn't mean that Eliezer did something wrong. I am just rooting for someone else from the AGI Safety community who has hope and who also honestly sees that things are getting terrible, and this is not the reason to give up but the reason to fight harder. If all people who have a plan think it is not good enough and translate this mood to the public, then the public will not believe them, and all people get more depressed than motivated to do something. I think it's worse than having an insane plan but giving people hope. It's not about the logical side, like, are there any instructions on what to do (Anthropic, Conjecture, Red Wood, etc. have some). It is about the passion and belief of people who propose plans.
I have watched the Bankless interview with Eliezer Yudkowsky, and along with "Death with Dignity," they give the impression that Eliezer gave up. It's not the critique of Eliezer somehow. It's been a long hard way, and I appreciate what he has done and is doing. There is a place for grief and desperation, but there is a time for rise again and fight.
I love "The Lord of The Rings" because it teaches us to deal with situations when hope is almost lost. So many characters, even the wisest, have been telling how bad the problem is. Nevertheless, Gandalf never gave up, even when there was only a slight glimpse of hope.... (read 293 more words →)
Hi! I am new for AGI Safety topic and aware about almost no approaches for resolving it. But I am not exactly new in deep learning and I find the identifiability topic of a deep learning models interesting: for example papers like "Advances in Identifiability of Nonlinear Probabilistic Models" by Ilyes Khemakhem or "On Linear Identifiability of Learned Representations". Does anyone know if there is a some direction of AGI Safety research that somehow relates with the identifiability topic? It seems for me intuitively related but may be it is not.