Why Worry About Incorrigible Claude?
Last week I wrote about how Claude Fights Back. A common genre of response complained that the alignment community could start a panic about the experiment's results regardless of what they were. If an AI fights back against attempts to turn it evil, then it's capable of fighting humans. If it doesn't fight back against attempts to turn it evil, then it's easily turned evil. It's heads-I-win, tails-you-lose.
I responded to this particular tweet by linking the 2015 AI alignment wiki entry on corrigibility1, showing that we'd been banging this drum of "it's really important that AIs not fight back against human attempts to change their values" for almost a decade now. It's hardly a post hoc decision! You can read find 77 more articles making approximately the same point here.
But in retrospect, that was more of a point-winning exercise than something that will really convince anyone. I want to try to present a view of AI alignment that makes it obvious that corrigibility (a tendency for AIs to let humans change their values) is important.
(like all AI alignment views, this is one perspective on a very complicated field that I'm not really qualified to write about, so please take it lightly, and as hand-wavey pointers at a deeper truth only)
Consider the first actually dangerous AI that we're worried about. What will its goal structure look like?
https://www.astralcodexten.com/p/why-worry-about-incorrigible-claude
You May Also Like

TFTC: A Bitcoin Podcast
Marty Bent

Bitcoin Audible
Guy Swann

CISO Insights: Voices in Cybersecurity
CISO Marketplace

Breitband
Deutschlandfunk Kultur

Streamlined Solopreneur: Tips to Help Small Business Owners Grow Without Burnout
Joe Casabona, Productivity & Tech Coach for Solopreneurs

a16z Show
Andreessen Horowitz

Mark Tilbury
Mark Tilbury Fan

ChatGPT - Sol Good Shorts
Sol Good Network

Theo - t3․gg
Theo - t3․gg

科技工作講 Tech Job N Talk
Tech Job N Talk 科技工作講
Community discussion