113
AI's Future Hangs in the Balance With California Law
(gizmodo.com)
AI's future in California hangs in the balance.
Isn't California the Capitol of the world? ;-)
I really don't think that the AI guys want to be anywhere else.
If it were a country, it would be the fifth or sixth largest economy in the world. Not debating; just saying it can have a big impact.
load more comments
(1 replies)
Though it sounds extreme, there are a lot of smart people in the AI community who truly believe AI could end humanity.
No. There are not.
Believing anything resembling current tools has the capacity to end humanity in incontrovertible proof that you are not smart.
AI person reporting in. Without saying whether or not I personally believe that the current tools will lead to the end of humanity, I'll point out a few possibilities that I find concerning about what's going on:
-
The hype around AI is being used to justify mass layoffs, where humans are being replaced by tools that do a questionable job and can't really understand the things those humans could understand. Whether or not the AI can do as good of a job according to some statical measurement is less relevant than the fact that a human is less likely to make an extremely grave mistake and more likely to be able to recognize when that does happen. I'm concerned this will lead to cross-industry enshitification on an unprecedented scale.
-
The foundation models consume a huge amount of energy. The more impressive you want it to be, the more energy it needs. As long as the data centers which run them are dependent on fossil fuels, they'll be pumping a huge amount of carbon in the air just to do replace jobs that we didn't need to have replaced.
-
As these tools are used more and more, they're going to end up "learning" from content created by themselves instead of something that's closer to a ground truth. It's hard to predict what kind of degradation of service will come from this, but the more we create systems that rely on these tools, the more harm it will do to us.
-
Given the cost and nature of these tools, they're likely to yield the most benefit to moneyed interests that want to automate the systems that maintain their power and wealth. E.g. generating large amounts of convincing disinformation to manipulate the public into supporting politicians or policies that benefit a small number of wealthy people in the short term while locking humanity into a path towards destruction.
And none of this accounts for possible future iterations of AI tools that may be far more capable than what exists today. That future technology will most likely be controlled by powerful people who are primarily interested in using it to bolster the systems that keep them in power, to the detriment of humanity as a whole.
Personally I'm far less concerned about a malicious AI intentionally doing harm to humanity than AI being used as a weapon by unscrupulous people.
I agree with everything you said and wanted to point out that you offered quite a compelling argument that even current AI tools are capable of significant amounts of damage without even touching on the autonomous weapons systems that are starting to be deployed.
Not even just talking about the military intelligence systems that may or may not have been deployed (Israel: Lavender et al), but we're starting to show off weapons platforms that may someday be empowered to perform their own threat analysis and take real world actions accordingly. That shit is terrifying in more of a Terminator/Matrix way than anything else imo.
Zero of these things are impacted by this legislation in any way.
This is exclusively the mentally unstable "killer AI" nonsense. We're not even 1% of 1% of the way to anything resembling agency.
It’s good for marketing, though. “Ah, our software is so powerful, it could destroy humanity! Please pass a bill saying so while we market friendly chatbots to the public while actually making money by selling our products to despots and warmongers that might actually end humanity.”
It's regulatory capture. Add deluded barriers to entry to make it difficult for competition and community projects to develop, and you have a monopoly.
Sure, but this outcome is not at all surprising. There are plenty of smart AI people that have nuanced views of what kind of threat could be posed by recklessly unleashing tools that we don't fully understand into the hands of people who are likely to do harmful things with them.
It's not surprising that those valid nuanced concerns get translated into overly simplistic misrepresentations entangled with pop sci fi panic around rogue AI as they try to move into public discourse.
We do fully understand them. Not knowing the exact reason they come to a model doesn't mean the algorithm has a shred of mystery involved. It's like saying we don't understand fluid dynamics because it's computationally heavy.
It's autocomplete with a really big training set and a really big model. It cannot possibly develop agency. It's hundreds of orders of magnitude of complexity short of a human.
That's not what an algorithms researcher means when we talk about "understanding". Obviously we know the mechanism by which it operates, it's not an unknown alien technology that dropped into our laps.
Understanding an algorithm means being able to predict the characteristics of its outputs based on the characteristics of its inputs. E.g. will it give an optimal solution to a problem that we pose? Will its response satisfy certain constraints or fall within certain bounds?
Figuring this stuff out for foundation models is an active area of research, and the absence of this predictability is an enormous safety concern for any use cases where the output can be consequential.
It cannot possibly develop agency.
I don't believe I've suggested anywhere that I think it will, but I'll play around with this concern anyway... There's a lot of discussion going on about having models feed back on themselves to learn from their own output. I don't find it all that hard to imagine that something we could reasonably consider self awareness could be formed by a very complex neural network that is able to consume and process its own outputs. And once self awareness starts to form, it's not that hard for me to imagine a sense of agency following. I have no idea what the model might use that agency for, but I don't think it's all that far fetched to consider the possibility of it happening.
There are plenty of nondeterministic algorithms. It's not a special trait. There are plenty of algorithms with actual emergent behavior, which LLMs don't have to any meaningful extent. We absolutely understand how LLMs work
The answer to both of your questions is not some unsolved mystery. It's "of course not". That's not what they do and fundamentally requires a much more complex architecture to even approach.
Non-deterministic algorithms such as Monte Carlo methods or simulated annealing can still be constrained to an acceptable state space. How to do this effectively for LLMs is a very open question, largely because the state space of the problems that they are applied to is incomprehensibly huge.
load more comments
(9 replies)
AI takes a crazy amount of power, which is largely fueled by the same fossil fuels that are indeed killing us off and destroying our habitat, which will kill even more of us, so AI could definitely indirectly kill off humanity.
If we get killed by auto complete we deserve to die.
SB 1047 is a California state bill that would make large AI model providers – such as Meta, OpenAI, Anthropic, and Mistral – liable for the potentially catastrophic dangers of their AI systems.
Now this sounds like a complicated debate - but it seems to me like everyone against this bill are people who would benefit monetarily from not having to deal with the safety aspect of AI, and that does sound suspicious to me.
Another technical piece of this bill relates to open-source AI models. [...] There’s a caveat that if a developer spends more than 25% of the cost to train Llama 3 on fine-tuning, that developer is now responsible. That said, opponents of the bill still find this unfair and not the right approach.
In regards to the open source models, while it makes sense that if a developer takes the model and does a significant portion of the fine tuning, they should be liable for the result of that...
But should the main developer still be liable if a bad actor does less than 25% fine tuning and uses exploits in the base model?
One could argue that developers should be trying to examine their black-boxes for vunerabilities, rather than shrugging and saying it can't be done then demanding they not be held liable.
In regards to the open source models, while it makes sense that if a developer takes the model and does a significant portion of the fine tuning, they should be liable for the result of that...
This kind of goes against the model that open source has operated on for a long time, as providing source doesn't represent liability. So providing a fine-tuned model shouldn't either.
So providing a fine-tuned model shouldn't either.
I didn't mean in terms of providing. I meant that if someone provided a base model, someone took that and but on of it, then used it for a harmful purpose - of course the person modified it should be liable, not the base provider.
It's like if someone took a version of Linux, modified it, then used that modified version for a similar person - you wouldn't go after the person who made the unmodified version.
It’s also not clear if it’s even possible to fully prevent AI systems from misbehaving. The truth is, we don’t know a lot about how LLMs work, and today’s leading AI models from OpenAI, Anthropic, and Google are jailbroken all the time. That’s why some researchers are saying regulators should focus on the bad actors, not the model providers.
It seems a complicated debate. Hard to find out where you want to stand. I want to show a method to find answers by creating 3 variants of an analogy.
For how many of these cases do you think somebody should be doing something?
Case 1:
A huge warehouse full of firearms. Burglars are breaking into it every night and stealing lots of weapons. The owners say they don't know how this warehouse was built and how to make it more secure in order to stop the criminals from obtaining lots of new weapons every day. The general public starts calling to the government to do something. Some say the warehouse owner should take responsibility. Others say it all depends on how the criminals use the weapons. The criminals seem to know how to use them good...
Case 2:
A huge warehouse full of hammers. Burglars are breaking into it every night and stealing lots of hammers. The owners say they don't know how this warehouse was built and how to make it more secure in order to stop the criminals from obtaining lots of new hammers every day. The general public starts calling to the government to do something. Some say the warehouse owner should take responsibility. Others say it all depends on how the criminals use the hammers. The criminals seem to know how to use them good...
Case 3:
A huge warehouse full of tulips. Burglars are breaking into it every night and stealing lots of flowers. The owners say they don't know how this warehouse was built and how to make it more secure in order to stop the criminals from obtaining lots of new flowers every day. The general public starts calling to the government to do something. Some say the warehouse owner should take responsibility. Others say it all depends on how the criminals use the tulips. The criminals seem to know how to use them good...
Are warehouse owners analogous to AI companies here? I don't think AI companies care about their models being misused unless it has economic impact whereas warehouse owners certainly care about their wares being stolen regardless of how those wares are then used or how dangerous they are.
I don't think AI companies care about their models being misused
Yes, that is one of the current questions, if you have read the article: Should they care?
It is a serious question, because if the models are misused, that could be a threat to all mankind - much worse than a warehouse full of weapons. And if they are required to care, then they might have to rebuild their models fundamentally, and they don't know how.
This bill seems somewhat misguided. How in the hell is something like a large language model going to cause a mass casualty incident? What I am more worried about is things that could more realistically pose a danger. What if robotic dogs patrolling the border have machine guns mounted on their backs, then a child does something unexpected and the robot wipes out an entire family? What if a self driving car suddenly takes off at full speed through a parade? They are trying to slot AI into everything now, and it will inevitably end up in some places that are going to cause loss of life. But chatbots? Give me a break.
load more comments
(1 replies)
Everyone: "AI is using too much energy!"
Legislators: "I shall make companies liable for terminators."
America: gun shops and manufacturers are shielded from lawsuits. Guns don't kill people, people kill people.
Also America: someone might learn how to make a bomb from an AI instead of learning it in the many many other places. Better sue.
Inconsistent. I can't sue because my kids school have to have a constant police presence.
Still. I think putting the brakes on “AI” is the right move right now. With its energy usage, intellectual property theft, nonconsensual (and underage) porn generating…not to mention its use by the ownership class to take and commodify human expression away from humans and the capitalist motive to profit over any consideration for the ramifications for the working class…I think halting this until we can get some protections in place for those this tech seems determined to exploit is a good thing.
Not that any of those problems will be solved even if we did hit the brakes. But, theoretically, yeah. I’m about it. Because, true to capitalist form, we are worsening the problems we haven’t even started trying to solve.
intellectual property theft
It's exactly like banks or huge companies: steal one movie, and you go to jail and pay a big fine. Steal all the movies, and suddenly it's not a problem anymore.
load more comments
(14 replies)
I already downloaded all the open source self hosted stuff and ain't gonna delete it. Get wrecked California state legislature.
From the article:
SB 1047 is a California state bill that would make large AI model providers – such as Meta, OpenAI, Anthropic, and Mistral – liable for the potentially catastrophic dangers of their AI systems.
The article lies about what's in the bill. No idea why.
https://leginfo.legislature.ca.gov/faces/billNavClient.xhtml?bill_id=202320240SB1047
view more: next ›
this post was submitted on 06 Jul 2024
113 points (91.2% liked)
Technology
58164 readers
3951 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS