
A decade ago today, Paul Christiano published "Prosaic AI alignment" on his well-known AI safety blog. Alongside Concrete Problems in AI Safety it became a foundational text in the increasingly-empirical AI safety field, spawning the prosaic alignment paradigm as more or less the standard way of thinking, even if people forgot the original arguments.
I thought this would be a nice day to have a look back at this classic post.
Prosaic AI alignment
(Related: a possible stance for AI control.)
It's conceivable that we will build “prosaic” AGI, which doesn’t reveal any fundamentally new ideas about the nature of intelligence or turn up any “unknown unknowns.” I think we wouldn’t know how to align such an AGI; moreover, in the process of building it, we wouldn’t necessarily learn anything that would make the alignment problem more approachable. So I think that understanding this case is a natural priority for research on AI alignment.
In particular, I don’t think it is reasonable to say “we’ll know how to cross that bridge when we come to it,” or “it's impossible to do meaningful work without knowing more about what powerful AI will look like.” If you think that prosaic AGI [...]
---
Outline:
(00:38) Prosaic AI alignment
(01:34) 1. Prosaic AGI
(03:35) 2. Our current state
(03:40) 2a. The concern
(05:51) 2b. Behaving cautiously
(07:41) 2c. The current state of AI alignment
(09:59) 3. Priorities
(10:12) 3a. Easy to start now
(11:48) 3b. Importance
(14:37) 3c. Feasibility
(17:38) Conclusion
The original text contained 2 footnotes which were omitted from this narration.
---
First published:
November 19th, 2026
Source:
https://www.lesswrong.com/posts/pfZWd2dLy7wRaDKYa/prosaic-ai-alignment-10-years-later
---
Narrated by TYPE III AUDIO.
Flere episoder fra "LessWrong (30+ Karma)"



Gå ikke glip af nogen episoder af “LessWrong (30+ Karma)” - abonnér på podcasten med gratisapp GetPodcast.








