God Help Us, Let's Try To Understand AI Monosemanticity
You've probably heard AI is a "black box". No one knows how it works. Researchers simulate a weird type of pseudo-neural-tissue, "reward" it a little every time it becomes a little more like the AI they want, and eventually it becomes the AI they want. But God only knows what goes on inside of it.
This is bad for safety. For safety, it would be nice to look inside the AI and see whether it's executing an algorithm like "do the thing" or more like "trick the humans into thinking I'm doing the thing". But we can't. Because we can't look inside an AI at all.
Until now! Towards Monosemanticity, recently out of big AI company/research lab Anthropic, claims to have gazed inside an AI and seen its soul. It looks like this:
https://www.astralcodexten.com/p/god-help-us-lets-try-to-understand
You May Also Like

Theo - t3․gg
Theo - t3․gg

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

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