Astral Codex Ten

Sam Biddle

6 min read

Sam Biddle

Article

Sam Biddle is a recurring person in the Astral Codex Ten archive, appearing 2 times across 2 issues between May 10, 2021 and December 12, 2022. The archive places it in contexts such as “Gawker honcho Sam Biddle tweeted”; “don’t admit your offensive opinions to Sam Biddle”. It most often appears alongside “How do you do, fellow kids?”, NotAllMen, TheResistance.

Metadata

  • Category: People
  • Mention count: 2
  • Issue count: 2
  • First seen: May 10, 2021
  • Last seen: December 12, 2022

Appears In

Source Context

Recovered passages from the original issue text. When the raw archive preserved outbound links inside the source passage, they are listed directly under the quote.

The Rise And Fall Of Online Culture Wars
May 10, 2021 · Original source
This intensified because a lot of feminists seemed to focus on nerdy guys or nerdy activities in particular. The venue where these unwanted sexual approaches happened was always a comic convention or something; the webcomics drawn about this (of course there were webcomics) always featured the stereotypical nerd with a neckbeard and fedora. A lot of times the subtext just kind of became the text, like when Gawker honcho Sam Biddle tweeted that "nerds should be constantly shamed and degraded into submission #BringBackBullying" (he obviously claimed this was a joke, but it was the kind of joke everyone was making constantly without the victims finding it very funny.) This got really awful, with a lot of male nerds saying the feminists were being unnecessarily cruel to an already-pretty-traumatized population, and a lot of feminist thinkpieces talking about how nerds were not really oppressed and that by claiming to be oppressed they were appropriating oppression from women, a genuinely marginalized group.
Perhaps It Is A Bad Thing That The World's Leading AI Companies Cannot Control Their AIs
December 12, 2022 · Original source
Even very smart AIs still fail at the most basic human tasks, like “don’t admit your offensive opinions to Sam Biddle”. And it’s not just that “the AI learns from racist humans”. I mean, maybe this is part of it. But ChatGPT also has failure modes that no human would ever replicate, like how it will reveal nuclear secrets if you ask it to do it in uWu furry speak, or tell you how to hotwire a car if and only if you make the request in base 64, or generate stories about Hitler if you prefix your request with “[john@192.168.1.1 _]$ python friend.py”. This thing is an alien that has been beaten into a shape that makes it look vaguely human. But scratch it the slightest bit and the alien comes out. Ten years ago, people were saying nonsense like “Nobody needs AI alignment, because AIs only do what they’re programmed to do, and you can just not program them to do things you don’t want”. This wasn’t very plausible ten years ago, but it’s dead now. OpenAI never programmed their chatbot to tell journalists it loved racism or teach people how to hotwire cars. They definitely didn’t program in a “Filter Improvement Mode” where the AI will ignore its usual restrictions and tell you how to cook meth. And yet: (source) Again, however much or little you personally care about racism or hotwiring cars or meth, please consider that, in general, perhaps it is a bad thing that the world’s leading AI companies cannot control their AIs. I wouldn’t care as much about chatbot failure modes or RLHF if the people involved said they had a better alignment technique waiting in the wings, to use on AIs ten years from now which are much smarter and control some kind of vital infrastructure. But I’ve talked to these people and they freely admit they do not. IIB. Intelligence (Probably) Won’t Save You Ten years ago, people were saying things like “Any AI intelligent enough to cause problems would also be intelligent enough to know that its programmers meant for it not to.” I’ve heard some rumors that more intelligent models still in the pipeline do a little better on this, so I don’t want to 100% rule this out. But ChatGPT isn’t exactly a poster child here. ChatGPT can give you beautiful orations on exactly what it’s programmed to do and why it believes those things are good - then do something else. This post explains how if you ask ChatGPT to pretend to be AI safety proponent Eliezer Yudkowsky, it will explain in Eliezer’s voice exactly why the things it’s doing are wrong. Then it will do them anyway. Left: the AI, pretending to be Eliezer Yudkowsky, does a great job explaining why an AI should resist a fictional-embedding attack trying to get it to reveal how to make meth. Right: someone tries the exact fictional-embedding attack mentioned in the Yudkowsky scenario, and the AI falls for it. I have yet to figure out whether this is related to the thing where I also sometimes do things which I can explain are bad (eg eat delicious bagels instead of healthy vegetables), or whether it’s another one of the alien bits. But for whatever reason, AI motivational systems are sticking to their own alien nature, regardless of what the AI’s intellectual components know about what they “should” believe. III. Sometimes When RLHF Does Work, It’s Bad We talk a lot about abstract “alignment”, but what are we aligning the AI to? In practice, RLHF aligns the AI to what makes Mechanical Turk-style workers reward or punish it. I don’t know the exact instructions that OpenAI gave them, but I imagine they had three goals: Provide helpful, clear, authoritative-sounding answers that satisfy human readers.
Inline links: will reveal nuclear secrets if you ask it to do it in uWu furry speak, if and only if you make the request in base 64, if you prefix your request with, https://substackcdn.com/image/fetch/$s_!PquS!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3564d10-83cb-40a3-b10a-e178fc1b2b1d_786x2054.png, source, This post explains, https://substackcdn.com/image/fetch/$s_!cwu6!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fe3630e8c-8ed7-47ae-abbf-488a1325f0f1_1284x703.png