alignment
Article
alignment is a recurring concept in the Astral Codex Ten archive, appearing 2 times across 2 issues between August 06, 2021 and December 05, 2023. The archive places it in contexts such as “actions by institutes working on alignment or whatever are necessarily misguided”; “sniping at alignment people even though they’re her natural allies”. It most often appears alongside AGI, Metaculus, OpenAI.
Metadata
- Category: Concepts
- Mention count: 2
- Issue count: 2
- First seen: August 06, 2021
- Last seen: December 05, 2023
Appears In
Related Pages
-
- AGI (2 shared issues)
-
- Metaculus (2 shared issues)
-
- OpenAI (2 shared issues)
-
- @AISafetyMemes (1 shared issues)
-
- @betafuzz (1 shared issues)
-
- Adam D’Angelo (1 shared issues)
-
- Aella (1 shared issues)
-
- AI (1 shared issues)
-
- AI Impacts (1 shared issues)
-
- AI risk (1 shared issues)
-
- algorithmic bias (1 shared issues)
-
- AlphaGo (1 shared issues)
External Links
Source Context
Recovered passages from the original issue text. When the raw archive preserved outbound links inside the source passage, they are listed directly under the quote.
Now, I don't think _actions_ by institutes working on alignment or whatever are necessarily misguided. I'm happy for us to have people looking into deflecting asteroids, aligning basilisks, eradicating sun-eating bacteria, or whatever. It's more that I find the conversations of some groups I'd otherwise have quite a lot in common with, very off-putting. Maybe it's hard to motivate yourself to work on low probability high-impact things without convincing yourself that they're secretly high probability, but I generally find the attitude unpleasant to interact with.
I feel bad making these reasonable arguments, because I also think we should do a lot of extremely theoretical work trying to figure out the exact way the far future is going to go and prepare for it, for reasons described in this Eliezer Yudkowsky essay.
Inline links: this Eliezer Yudkowsky essay
In conclusion, AI is like a caveman fighting a three-headed dog in Constantinople. The dog is trying to summon a demon, and the demon is going to unleash a genie. The caveman could fight the demon if he had nuclear weapons, but all he has is an antique musket, and also, just yesterday an eminent physicist told him that nuclear fission was “the merest moonshine”. He could escape the genie if he had a Mars rocket, but nobody can solve the rocket alignment problem, and also Mars might already be overpopulated. If only there had been some kind of fire alarm that could have warned him of this!
…but not continue to lead the Superalignment team? I’m confused by this; why wouldn’t he? Related:
Forecasters seem to lean toward the second hypothesis; at least I don’t see any big safety proponents on here (except Emmett, who I doubt is really being considered). Fei-Fei Li is an AI ethics person, but the kind who spends time sniping at alignment people even though they’re her natural allies and desperately want to help her. These people always do well for themselves, and I’ve bet her up. Most of the others are Silicon Valley businesspeople of one sort or another.