/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 www.cold-takes.com
Why AI alignment could be hard with modern deep learning
| | joecarlsmith.com
How do we solve the alignment problem? - Joe Carlsmith
4.8 parsecs away

Travel
| | Introduction to an essay series about paths to safe, useful superintelligence.
| | www.lesswrong.com
[Link] A minimal viable product for alignment - LessWrong
4.5 parsecs away

Travel
| | This is a link post for https://aligned.substack.com/p/alignment-mvp ...
| | scottaaronson.blog
Shtetl-Optimized » Blog Archive » My AI Safety Lecture for UT Effective Altruism
5.0 parsecs away

Travel
| | Two weeks ago, I gave a lecture setting out my current thoughts on AI safety, halfway through my year at OpenAI. I was asked to speak by UT Austin's Effective Altruist club. You can watch the lecture on YouTube here (I recommend 2x speed). The timing turned out to be weird, coming immediately after the...
| | scottaaronson.blog
Shtetl-Optimized » Blog Archive » OpenAI!
28.9 parsecs away

Travel
| I have some exciting news (for me, anyway). Starting next week, I'll be going on leave from UT Austin for one year, to work at OpenAI. They're the creators of the astonishing GPT-3 and DALL-E2, which have not only endlessly entertained me and my kids, but recalibrated my understanding of what, for better and worse,...