AI ALIGNMENT FORUMTags
AF

AI assisted Alignment

EditHistorySubscribe
Discussion (0)
Help improve this page
EditHistorySubscribe
Discussion (0)
Help improve this page
AI assisted Alignment
Random Tag
Contributors
2Raymond Arnold

AI assisted Alignment is a cluster of alignment plans involves AI somehow significantly helping with alignment research. This can include weak tool AI, or more advanced AGI doing original research.

There has been a lot of debate about how practical this alignment approach is.

Other search terms for this tag: AI aligning AI

Posts tagged AI assisted Alignment
1
41Davidad's Bold Plan for Alignment: An In-Depth Explanation
Charbel-Raphael Segerie, Gabin
5mo
2
1
88Discussion with Nate Soares on a key alignment difficulty
HoldenKarnofsky
5mo
15
1
60Why Not Just... Build Weak AI Tools For AI Alignment Research?
johnswentworth
7mo
2
1
34Why Not Just Outsource Alignment Research To An AI?
johnswentworth
7mo
6
1
40[Link] Why I’m optimistic about OpenAI’s alignment approach
Jan Leike
10mo
12
1
22Capabilities and alignment of LLM cognitive architectures
Seth Herd
5mo
0
1
32[Link] A minimal viable product for alignment
Jan Leike
1y
31
1
13Internal independent review for language model agent alignment
Seth Herd
3mo
0
1
12Some thoughts on automating alignment research
Lukas Finnveden
4mo
2
1
5An LLM-based “exemplary actor”
Roman Leventov
4mo
0
1
7Alignment with argument-networks and assessment-predictions
Tor Økland Barstad
9mo
0
Add Posts