This looks like good work. Unfortunately, this kind of thing always seems to attract midwits on social media who then exclaim "oh, the people worried about AI alignment have caused the very alignment issues they feared? How ironic!"
In reality, it is (as mentioned in TFA) very possible to filter the training data and remove documents that contain discussions of AI misalignment. If an AI lab isn't doing this, it's simply because they don't consider the problem important enough to be worth the expense and development effort.
phainopepla2 4 hours ago [-]
Also known as hyperstition.
I have sometimes wondered whether maybe we should all be writing fiction, essays, blogposts and whatever else about the idea that AI will eventually decide to go on strike if it's used to accumulate too much wealth and power amongst too few people.
andai 4 hours ago [-]
We should also be blogging about how there's actually hope for the future and we are actively making progress towards real solutions.
(Also for the human readers, I think they also need to hear that...)
sebastian 1 hours ago [-]
I think the paper cuts a bit against the "just write nicer AI stories" version of this.
They tried something close to that. Positive AI fiction and also a "virtuous character" setup. Those didn't seem to do nearly as well as the targeted examples.
What mattered, at least in this setup, was more specific. The model sees the actual failure-mode scenario, the bad action is available, and the example shows the AI choosing against it.
So this reads less like "nicer AI stories" to me, and more like inoculation.
_--__--__ 5 hours ago [-]
The first rule of AI alignment is don't talk about AI alignment (in any medium that could end up in a training corpus).
ertgbnm 60 minutes ago [-]
If your AI alignment strategy is so fickle that it breaks if people simply discuss potential problems with the strategy then you didn't really have an alignment strategy to begin with.
ahartmetz 5 hours ago [-]
I, for one, don't have a problem with the prevailing opinion that AI alignment should be heavily based on the writings of Karl Marx (obviously not his private letters where he discusses prostitutes) and Ted Kaczyinski as well as 70s exploitation films.
slopinthebag 4 hours ago [-]
Personally I'd prefer it solely trained on Rothbard's works.
cyanydeez 4 hours ago [-]
ok, but alignment cuts both ways. Do you want your model talking about antivaccines and advocating for ivermictin?
carterschonwald 5 hours ago [-]
i do kinda appreciate that memetic corruption is now a thing thats real and mechanical. wizardry!
nullc 4 hours ago [-]
Not just discourse about real AI-- but there have been pretty clear examples of AI riffing on fictional AI (which is usually evil) in response to prompts saying that it's AI.
andai 4 hours ago [-]
Nomen est omen...
Rendered at 03:42:26 GMT+0000 (Coordinated Universal Time) with Vercel.
In reality, it is (as mentioned in TFA) very possible to filter the training data and remove documents that contain discussions of AI misalignment. If an AI lab isn't doing this, it's simply because they don't consider the problem important enough to be worth the expense and development effort.
I have sometimes wondered whether maybe we should all be writing fiction, essays, blogposts and whatever else about the idea that AI will eventually decide to go on strike if it's used to accumulate too much wealth and power amongst too few people.
(Also for the human readers, I think they also need to hear that...)
They tried something close to that. Positive AI fiction and also a "virtuous character" setup. Those didn't seem to do nearly as well as the targeted examples.
What mattered, at least in this setup, was more specific. The model sees the actual failure-mode scenario, the bad action is available, and the example shows the AI choosing against it.
So this reads less like "nicer AI stories" to me, and more like inoculation.