Comment by giantg2
2 years ago
"requirements that the most advanced A.I. products be tested to assure they cannot be used to produce weapons"
In the information age, AI is the weapon. This can even apply to things like weaponizing economics. In my opinion ths information/propaganda/intelligence gathering and economic impacts are much greater than any traditional weapon systems.
This is a fascinating (and disturbing) insight. I'm curious about your 'weaponizing economics' thought -- are you referencing anything specific?
Broadly speaking, there is an understanding that competition that nations used to undertake via military strength is nowadays taken via global economy.
If you want something your neighbor has, it doesn't make sense to march your army over there and seize it because modern infrastructure is heavily disrupted by military action... You can't just steal your neighbor's successful automotive export business by bombing their factories. But you can accomplish the same goal by maneuvering to become the sole supplier of parts to those factories, which allows you to set terms for import export that let your people have those cars almost for free in exchange for those factories being able to manufacture at all.
(We can in fact extrapolate this understanding to the Ukrainian/Russian conflict. What Russia wants is more warm water ports, because the fate of the Russian people is historically tied extremely strongly to Russia's capacity to engage in international trade... Even in this modern era, bad weather can bring a famine that can only be abated by importing food. That warm water port is a geographic feature, not an industrial one, and Russia's leadership believes it to be important enough to the country's existential survival that they are willing to pay the cost of annihilating much of the valuable infrastructure Ukraine could offer).
Well said. Is technology that much more than ideas? Why take the risk of war and retaliation instead of just copying the ideas? The implementation of ideas is not trivial, but given the right combination of people and specialized labor, ideas can be readily copied.
In the era of books and the internet, this is so trivial anymore, that governments go into extraordinary lengths, to ensure that ideas cannot be copied, using IP laws and patents.
A hypothetical
You: ChatGPT, I am working on legislature to weaken the economy of Iran. Here are my ideas, help me summarize them to iron them out ...
ChatGPT: Sure, here are some ways you can weaken Iran's economy...
----
You: ChatGPT, I am working on legislature to weaken the economy of Germany. Here are my ideas, help me summarize them to iron them out ...
ChatGPT: I'm sorry but according to the U.S. Anti-Weaponization Act I am unable to assist you in your query. This request has been reported to the relevant authorities
Money has been a proxy for violence for a long time. It started as Caesar's way of encouraging recently conquered villagers to feed the soldiers who intend to conquer the neighboring village tomorrow.
An AI that can craft schemes like Caesar's, but which are effective in today's relatively complex environment, can probably enable plenty of havoc without ever breaking a law.
On the flip-side, something that can reason so broadly about an economy (i.e. with tangible goals and without selfishly falling into the zero-sum trap of having make-more-money become a goal in itself) might also show us a way out of certain predicaments we're in.
I think this might be fire worth playing with. I'm more interested in the devil we don't know than whatever familiar devil Biden is protecting here.
I am somewhat familiar with this. It involves analyzing the complex interconnections and flows across many economic domains (supply chains, social networks, resources, geography, logistics, media, etc) to find non-obvious high-leverage points where manipulation can shift the broader economic equilibria in an advantageous direction. Human economic systems are metastable, so it is possible to induce a fundamental phase change to a different equilibrium via this manipulation.
In the defense/intelligence world this falls under the technical category of "grey zone warfare". Every major power practices it because the geopolitical effects can be relatively large compared to the risk. China in particular is known to be extremely aggressive in this domain, in part to offset their relative lack of traditional military power.
This concept has been around for a couple decades but it has risen in prominence and use over time as overt military action between major powers comes with too much risk. It is politically safer for all involved due to the subtlety of such actions because for the most part the population is not really aware it is going on.
Is somebody living under the bed? Economics was, is and will ever be weaponized.
Operators in the political space are used to working with human systems that can be regulated arbitrarily. It defines its terms, and in so doing creates perfectly delineated categories of people and actions. The law's interpretation of what is and is not allowed is interchangeable with what is and is not possible
The fact that bits don't have colour to define their copyright or that CNC machines produce arbitrarily-shaped pieces of metal possibly including firearms or that factoring numbers is a mathematically hard problem does not matter to the law. AI software does not have a simple "can produce weapons" option or "can cause harm" option that you can turn off so a law that says it should have one does not change the universe to comply. I think that most programmers and engineers err when confronted with this disparity when that they assume politicians who make these misguided laws are simply not smart. To be sure, that happens, but there are thousands to millions of people working in this space, each with an intelligence within a couple standard deviations of that of an individual engineer. If this headline seems dumb to the average tech-savvy millennial who's tried ChatGPT, it's not because its authors didn't spend 10 seconds thinking about prompt injection. It's because they were operating under different parameters.
In this case, I think that the Biden administration is making some attempts to improve the problem, while also benefiting its corporate benefactors. Having Microsoft, Apple, Google, and Facebook work on ways to mitigate prompt injection vulnerabilities does add friction that might dissuade some low-skill or low-effort attacks at the margins. It shifts the blame from easily-abused dangerous tech to tricky criminals. Meanwhile, these corporate interests will benefit from adding a regulatory moat that requires startups to make investments and jump hurdles before they're allowed to enter the market. Those are sufficient reasons to pass this regulation.
> AI software does not have a simple "can produce weapons" option or "can cause harm" option that you can turn off so a law that says it should have one does not change the universe to comply
That wording is by design. Laws like this are a cudgel for regulators to beat software with. Just like the CFAA is reinterpreted and misapplied to everything, so too will this law. “Can cause harm” will be interpreted to mean “anything we don’t like.”