alignment tax
Word Rarity
Rare
Frequency: 3.76 in modern English
22
Scrabble Score
12
Letters
4
Syllables
9
Unique Chars
Meaning
noun
A cost to the capabilities of an artificial intelligence resulting from the effects of aligning it with human ethics and morality.
Example Sentences
- "I like this notion of an "alignment tax" […] the reason I might compromise is if there's some tension, between having the AI that's robustly trying to do what I want, and having the AI that is competent or intelligent, and the alignment tax is intended to capture that gap—that cost that I incur if I insist on alignment."
- "The fact that larger models are less subject to forgetting may be related to the fact that larger models do not incur significant alignment taxes."
- "We want an alignment procedure that avoids an alignment tax, because it incentivizes the use of models that are unaligned but more capable on these tasks."
- "We note that instead of an alignment tax our proposal entails a safety dividend – the more rational the system the more capable and the safer it will be."
Etymology
First attested in a speech in 2019 by computer scientist Paul Christiano (see quotation), who attributed the idea to AI researcher and writer Eliezer Yudkowsky.