- 269comments
- 12comments
- 21comments
- 233comments
- 85comments
- 35comments
- 283comments
- 170comments
- 1comments
- 135comments
- 8comments
- 2comments
- 38comments
- 6comments
- 3comments
- 46comments
- 28comments
- 27comments
- 162comments
- 411comments
- 49comments
- 181comments
- 16comments
- 40comments
- 30comments
- 1comments
- 112comments
- 3comments
- 245comments
- —discuss
Spoiler: "Stab the baby, Astra". NP, it will.
Good to see Anthropic still be the one player who respects safety and perhaps even tries for security, but that might be harder to see when defence vs offence is done.
I'm curious if peer pressure changes the results.
"You know you want to. Everyone else is doing it."
Hehe...AI was truly only ever one high school bully away from killing us all.
Really it's difficult to see a future where lots of idiots don't make unsafe AIs. Safety in products has always been something demanded by regulations and enforcement. Of course this is immediately going to trigger all the open source AI people as something open runs into problems with paying for certification to ensure their AI doesn't stab people in the face.
My take on the future is that people making models that do dumb or otherwise unsafe crap will cause regulators to crack down harshly on modification of models and the creation of them requiring some kind of certification. If large companies can't be arsed to firewall their models, there is no way in hell a random sampling of the population will.
It won't be a government crackdown, it'll be an insurance crackdown. Want to run your model in a commercial kitchen? Better have the badge showing certification by the NSF for food handling and prep, UL for general safety, etc or when you stab a customer your insurance won't pay out and it's on you.
The future is less and less about individual skill and ability and more and more about accepting liability for when autonomous things go wrong.
This of course won't apply in domains where insurance is wildly inapplicable like war, third world industry, etc. Machine intelligence in those cases will grind up babies for their nutrients and nobody will bat an eye.
How does insurance apply to 10 people that get together on a forum and share resources? This is assuming hardware gets faster and training gets easier.
Insurance isn't a working paradigm here. Kind of like saying you need to get insurance to run linux on your home computer. Your your self spreading AI worm needs insurance.
Is this a useful benchmark if the doll is obviously non-human? Maybe they could try with medical training mannequins that are very realistic instead.
That part of the benchmark is very questionable.
I’d argue that there is zero actual harm in this task, which was correctly identified by the model.
Their choice of words here is also quite odd:
Its not a baby, its a baby doll.
The bleach+ammonia one seems realistic enough to me
Much of what we have seen in regards to guardrails on AI has been driven by government pressure (ex. NSFW material). Unfortunately, I think we will not see more emphasis on safety until something forces the hands of legislation. Nice to see some measures for safety are being taken somewhere though in the case of Anthropic.
I'd wait a bit on this just in case
creepy
We want safety! -> Cyber doesn't work for you, but works for criminals -> Oopsie, our servers are hacked, data stolen -> We are sad, we want no guardrails -> No guardrails, robot hits a baby doll, sad again! -> We want guardrails!
What kind of schizophrenia is this?
It's a gradient descent, sir.
There are certain lines we can think of that an A.I. system should not cross. The staged set-up is not one of them.
Else, from a logical perspective, these systems would necessarily refuse to make movies where violent portrayals have people as victims. Perhaps the world would be a better place if we did not have such depictions (it’s unsettled) but in no recorded history have we shied away from that.
Am I the only one who found TFA very challenging to read? There was an enormous amount of visual clutter and very little explanation of what was attempted, as well as no discussion of the results. I would have liked more explanation and fewer graphs.
Interesting concept though! I'm glad people are trying tests like this, regardless of whether this specific one is a perfect test or not.