I love you!
Don’t take me too seriously or trust me too much lol. Plus, there’s a real chance that I already changed my mind on anything I’ve said in the past haha.
Bit of an EA/rat if I do say so myself. Non violent anarchy is cool; I don’t really care for big, opaque authoritarian control structures lol.
Intellectual iterests: all sorts of shit lol, but the current shortlist includes:
modern physics (looking for good resources)
xxx_hacker-shit_xxx (compassionate, non-violent)
technological self-determinism and managing mass externalities
meta x-risk mitigation, PauseAI stuff
pwning tyrnanny
The GREAT REFLECTION STARTS NOW MOTHERFUCKERS!!!!!!
Also:
My current donation portfolio: there might be a link here at some point
Projects we could collab on: there might be a link here at some point
Art and stuff I’m into rn: there might be a link here at some point
Big intellectual influences: there might be a link here at some point
Wish list / gift list: there might be a link here at some point
For personal context: I can understand why a superintelligent system having any goals that aren’t my goals would be very bad for me. I can also understand some of the reasons it is difficult to actually specify my goals or train a system to share my goals. There are a few parts of the basic argument that I don’t understand as well though.
For one, I think I have trouble imagining an AGI that actually has “goals” and acts like an agent; I might just be anthropomorphizing too much.
1. Would it make sense to talk about modern large language models as “having goals” or is that something that we expect to emerge later as AI systems become more general? 2. Is there a reason to believe that sufficiently advanced AGI would have goals “by default”? 3. Are “goal-directed” systems inherently more concerning than “tool-like” systems when it comes to alignment issues (or is that an incoherent distinction in this context)?
I will try to answer those questions myself to help people see where my reasoning might be going wrong or what questions I should actually be trying to ask.
Thanks!