Why are AI researchers constantly handicapping everything they do under the guise of ""safety""? It's a bag of data and some math algorithms that generate text....
I agree with the general premise of too much "safety", but this argument is invalid. Humans are bags of meat and they can do some pretty terrible things.
I don't think that anyone has any problems with stopping random AIs when they're doing crimes (or more realistically the humans making them do that) - but if you're going to make the comparison to humans in good faith, it'd be a person standing behind you, punishing you when you say something offensive.
Career and business self-preservation in a social media neurotic world. It doesn't take much to trigger the outrage machine and cancel every future prospect you might have, especially in a very competitive field flush with other "clean" applicants.
Just look at the whole "AI racism" fustercluck for a small taste.
So of course if this is where the money and interest flows then the research follows.
Besides, it's a generally useful area anyway. The ability to tweak behavior even if not done for "safety" still seems pretty useful.
Seriously. The reason why we dont have mass killings everywhere is not the fact that information on how to make explosive drones or poisons is impossible to find or access. It's also not so hard to buy a car or knife.
Hell you can even find YouTube videos on how exactly uranium enrichment works step by step. Even though some content creators even got police raided for that. Yet we dont see tons of random kids making dirty bombs.
PS: Cody's Lab: Uranium Refining:
another example is if a LLM could tell you exactly how to build a tabletop laser device that could enrich uranium for a few hundred thousand dollars.
The only "danger" LLM "safety" can prevent is generation of racist porn stories.
https://en.wikipedia.org/wiki/Separation_of_isotopes_by_lase...
It's the same with plenty of other things.
That describes almost every web server.
To the extent that this particular maths produces text that causes political, financial, or legal harms to their interests, this kind of testing is just like any other accepting testing.
To the extent that the maths is "like a human", even in the vaguest and most general sense of "like", then it is also good to make sure that the human it's like isn't a sadistic psychopath — we don't know how far we are from "like" by any standard, because we don't know what we're doing, so this is playing it safe even if we're as far from this issue as cargo-cults were from functioning radios.