ASI Self-Hacking Argument

Anthony Wang — Wed, 12 Feb 2025 22:03:44 -0500

Recently my friend Alek has been thinking a lot about ASI and existential risk, and even though I don’t believe his central claim at all, it’s still been interesting to discuss this stuff. Here’s a weird argument I came up with for why one specific theoretical form of ASI might not be harmful at all and actually quite useless. I’m probably not the first person to come up with this, so I’d like to know if there are any articles out there with similar arguments. Anyways, thanks to Alek for helping me fix some flaws and refine this argument!

The End

Anthony Wang — Mon, 03 Jun 2024 19:33:48 -0500

No, this post isn’t the end of my blog. But it is the end of a long saga that began 123 days ago…

A while back, my friend Alek posted a story on his blog. A week later, I wanted to write a parody of it in the exact same style. And so I came up with the idea of using only words from Alek’s original story, where each word in my story appears no more times than it appears in Alek’s story. And thus, the short story series was born! Some of my friends helped continue the chain, where story $i$ only uses words from story $i-1$, counting multiplicity. We also considered making a chain where story $i$ only uses words, counting multiplicity, that were in story $i-2$ but not story $i-1$, so basically the words left over from story $i-1$. It’s kind of like the Euclidean algorithm but more cursed. I guess this would converge on a small set of words that can’t form a sentence, like a bunch of copies of “the”.

Alek on Unnamed Website

ASI Self-Hacking Argument

The End