Different perspectives on concept extrapolation — AI Alignment Forum
At the recent EAGx Oxford meetup, I ended up talking with a lot of people (18 people, back to back, on Sunday - for some reason, that day is a bit of…
x Different perspectives on concept extrapolation — AI Alignment Forum Concept Extrapolation Value Learning AI Frontpage 24 Different perspectives on concept extrapolation by Stuart_Armstrong 8th Apr 2022 6 min read 8 24 At the recent EAGx Oxford meetup, I ended up talking with a lot of people (18 people, back to back, on Sunday - for some reason, that day is a bit of a blur). Naturally, many of the conversations turned to value extrapolation/concept extrapolation , the main current focus of our Aligned AI startup . I explained the idea I explained multiple times and in multiple different ways
related reading
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- What is AI alignment? - by Adam Jones - BlueDot Impactblog.bluedot.org
- The Artificiality of Alignmentjoinreboot.org
- 2023 letter | Zhengdongzhengdongwang.com
- The Universe from an Intentional Stancecasparoesterheld.com
- What Does It Mean to Align AI With Human Values? | Quanta Magazinequantamagazine.org
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
- Ilya Sutskever — We're moving from the age of scaling to the age of researchdwarkesh.com
- The Best of LessWrong — LessWronglesswrong.com
- My AI Model Delta Compared To Yudkowsky — LessWronglesswrong.com
- Alignment By Default — AI Alignment Forumalignmentforum.org
- Shah and Yudkowsky on alignment failures — LessWronglesswrong.com