Untrusted smart models and trusted dumb models — LessWrong
[Ryan Greenblatt originally made this point to me a while ago, and we then developed a bunch of these ideas together. Thanks to Paul Christiano and a…
Crossposted from the AI Alignment Forum . May contain more technical jargon than usual.
Read More
Other Stories in Science
- Talking to laymen about AI development — LessWrong
- FDA staff reviewing Elon Musk’s Neuralink were included in DOGE employee firings, sources say
- Takshashila University: The Glorious Legacy of Ancient Education
- "The Rise of Robots: Can They Fully Replace Humans?”
- Magnetic grip makes your iPhone more Leica camera
- Top 10 Coolest Gadgets on Amazon You Can Buy Right Now
- UBER Killing Robotaxi Launching in 120 Days
- How three fast cars used technology to change the future. (Part 2/2)
- Digital Studies: The Critical Road to Critical Thinking
.png)
