0444
Internet
Joined January 2016
- Tweets1.2K
- Following499
- Followers79
- Likes6.6K
Pinned Tweet
The basic argument is: there's some risk of the ASI ruin, if it's built. There is certainty of death for me & everyone I care about if it's not. I'm happy when alignment research pans out, and I work to increase the odds, but I oppose any research/advocacy making timelines longer
Witnessing the destruction of SIRCAA in Stalker 2 almost made me cry. One of the best locations in video games ever, perfectly reflecting my personal anesthetics and philosophy
I oppose slowing down AI development. But why is it that almost everyone who shares this view jumps to personal attacks on Aella, outrage by silly jokes by Scott, forms cancel mob on Wentworth, copes on AI4math or regulatory capture. There is almost no intelligent opposition left
For the past 15 years, I've been trying to answer the question about how to live my life. I'm finally reading Omohundro's paper on basic AI drives, and I'm surprised how much of his argument goes along the same lines as my thinking.
I was also thinking quite a lot about the Experience Machine. Omohundro's argument doesn't really hit the spot. To my own life, I apply one based on epistemic humility, in two flavours. First, it's difficult to fully know yourself, so committing to a wirehead might miss your true goals. Second, it loses critical agency: the convergent goal is usually immortality, and as the world changes, it's important to remain capable of action.
Finally, the last point I spent years thinking about: why not be a sociopath? Whatever my goals are, it seems that empathy and caring about others should be excised from myself. "Why not kill old lady Alyona Ivanovna" and all that. The key insight that got me unstuck was Hanson's "Elephant in the Brain" ideas of well-developed insightful agents. This is related to other decision-theoretic arguments about AI discussed on LessWrong, but Omohundro's paper predates these.
How did it all come to be,
That there should be such EMs as me?
The superiority of sex robots over women was revealed to me in a dream: thanks to built-in speakers, they can dirty talk during bjs
Retreat to an incomprehensibly sped-up virtual world simulation gf, hunt for immortality pursuing universe-scale engineering physics bf
Simulation Hypothesis, but instead of simulating brains it's only fully immersive VR, like in that famous Alan Watts quote
One of my favourite sequence of essays: "What you can't say" by PG, "The Kolmogorov option" by SA, "Kolmogorov complicity" by SSC. And now, their continuation is (despite the title..) "Beating woke with facts and logic" by NC.
And I realise that there is rich intellectual history behind them. Even from an angle close to me, "Theses on Hope and Hopelessness" by LK and "The Captive Mind" by CM, which I still haven't read. Soviet literature, in particular Solzhenitsyn, seems relevant. And back and back
Why are LLMs performing these weird internet searches? I asked ChatGPT to prove some differential geometry statements and it goes off looking up German police crime statistics and elderly care homes ads. I get that they're prob RL'ed to search, but why not at least sth related?