Low impact agency: review and discussion
Not on the map. Why?
Abstract (arXiv)
Powerful artificial intelligence poses an existential threat if the AI decides to drastically change the world in pursuit of its goals. The hope of low-impact artificial intelligence is to incentivize AI to not do that just because this causes a large impact in the world. In this work, we first review the concept of low-impact agency and previous proposals to approach the problem, and then propose future research directions in the topic, with the goal to ensure low-impactedness is useful in making AI safe.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 5 of its 23 references that are in the map. First posted on arXiv 6 Mar 2023.
Builds on
5 of 23 references.
References · 5
- 2022Adversarial Training for High-Stakes Reliabilitycited by 60
- 2018Penalizing side effects using stepwise relative reachabilitycited by 38
- 2019Conservative Agency via Attainable Utility Preservationcited by 35
- 2020Avoiding Side Effects By Considering Future Taskscited by 32
- 2017Low Impact Artificial Intelligencescited by 11
Built on by
Not cited yet.