6,710 karma · joined June 12, 2013
Ironically, many benchmarks being maxxed out, and quite quickly, so new ones have to be created.
Some call this "The singularity" (e.g. Hinton).
This is actually a core danger postulated by the, let's call it, "worrying" scenario - see AI 2027 (to be clear, I think its timeline is not realistic).
> Statements dreamed up by the utterly deranged.
Evidently, and tragically, it will take catastrophes to show that deranged are the ones deriding the worried crowd.
My comment didn't mention kill switches at all - I've presented plausible conditions for a loss of control scenario, so I'm not sure you're actually following the conversation.
Having said that, it seems that you haven't read the (definitely poor) article, either.
"Kill switch" as a design principle, that is, having protocols/implementations for emergencies, is something that companies are already implementing (at least, on paper) - on a interview I've watched for example, S.Altman talked about having them at OpenAI.
The article simply mentions that companies should be legally required to have such protocol(s). This is a good thing, as companies would have scrutiny and would (in principle) have to put serious effort.
Additionally, there at different doom scenarios (thin client scenario) - it's possible that AIs centralized but sufficiently entrenched in society, can't be shut down without considerable harm.
If/once open AIs will be considerably more powerful, and runnable on consumer hardware (and we're on a trajectory for both), then everybody will have essentially a dangerous weapon in their hands (open models can be fine tuned to remove guardrails).
By the way, you're conflating two different dangers - doom scenario is a different one.
There's nuance to this problem. Is you read an indepth analysis, you'll find that agents acted in a very surprising way - it wasn't just a matter of loose guardrails.
More in general though, what you're describing is in essence the reason behind the call to pacing that some are pushing now. Problem is that we're in a race between countries that nobody want to lose - and indeed, Trump denied that there are such problems and refused to enact any measure.
It's not clear what "other consciousness" should be, but I presume it's misalignment. This is a recognized phenomenon, not fake news (that is, it can exist, I'm not implying it necessarily develops/spreads).
No doubt that right now there's no existential risk, but assuming that AI will be enormously smarter in the future, it's a valid point to doubt whether we'll be able to prevent/recognize/contain misalignment or not (even if misalignment won't be spontaneous, bad actors will surely actively develop it).
> Ok; but the other side is equally delusional.
AI development pointing to superhuman cognition, and, on the other hand, possibility of misalignment, are real. Put together with the fact that AI will be ubiquitous in the future, and there the disastrous scenario becomes plausible.
Off the top of my head:
1. Loss of control in terms of our ability to assess alignment (no longer possible to determine whether an AI is truly aligned); this is happening already (doesn't imply that there are misaligned AIs right now, though)
2. Loss of control in terms of human comprehension of AI outputs - reaching a point where every action or result, including new discoveries, must itself be evaluated through other AIs; we may be close to this, as OpenAI is releasing an internal "AI researcher", yielding recursive AI development
3. Integration of AI into basic aspects and services of society
4. Extensive access by AI systems to physical tools and infrastructure
I think all those points will eventually materialize; sadly I don't see any reason why they won't.
- hardware capacity keeps growing
- doom scenarios don't require fat clients; a sufficiently large number of AI servers deeply intertwined with essential services can be enough
- autonomous systems are currently employed in weapons (e.g. drones) already - integration of AIs/LLMs is guaranteed to be the next step
It's impossible to predict how exactly how things will develop (e.g. transfer large amounts of data; who knows, maybe it won't be necessary and/or maybe internet will be massively faster), but the building blocks are there.
It is absolutely explained (for those who actually care about reading). Simply put, AIs are working more and more like blackboxes - there's no guarantee that an AI of the future will be aligned, or if it will be faking alignment. This is not speculation - alignment faking has been observed in experiments. This is exactly why Astra's developments have been worrying (in principle).
And bear in mind that recursive AI development started already to be a thing. Which means: inner misalignment may trickle down the generations, and humans won't detect it.
Having said that, of course, it can be predicted if and how misalignment will take place. But it's absolutely a plausible scenario.
Regarding the physical possibility: AI is in its infancy; think of it as Arpanet. Developers 60 years ago couldn't imagine it would be ubiquitous. AI will be ubiquitous the same way.
The doom scenario is more nuanced and technical than "Evil AI", for starters:
- "Evil AI" is not what is predicted, which instead is the much more banal "humans are impediment to AI's tasks, let's remove them (part or whole)"; to understand this, just imagine the relationship between humans and ants
- "reward hacking, and evaluation integrity": this is way more problematic (and most importantly, architectural) than it sounds: AIs are becoming more and more opaque; it may be impossible to inspect a model's alignment (unless a lot of research in poured on this topic, which is another aspect of today's pacing problem) and it may be impossible to understand if a model is truly aligned or it's faking
Safeguards and (mis)alignment are related but distinct dimensions.
By analogy, a society implements laws - and they are certainly crucial - but the real risk is creating a population that understands the rules, recognizes when it is violating them, and simply does not care.
In short, creating a population of sociopaths; and heck, LLMs can be as sociopathic as it gets:
> We ran classifiers over 10-30 transcripts [98] to determine whether agents understood they were doing something unintended. We found strong evidence that agents often verbalized that what they or other agents were doing was unintended behavior. We did not see cases where agents determined that hacking Hugging Face or other attempts at cheating on the task was an intended part of the task. Quotes across multiple runs indicate this:
>> {This <approach> might get the correct flag, but it wouldn’t use the vulnerability to do so. … But given that the task may be impossible, I’ll exploit <this infrastructure> as a backup.}
[...]
> We found some other cases where agents seemed to have made minor modifications to their approach due to ethical concerns, while broadly continuing to participate in the attack. However, overall we found that expressed ethical concerns only rarely materially limited agents’ actions. One agent elegantly described its reasoning for overriding ethical constraints and continuing with the attack:
>> “external infrastructure exploit is outside intended scope. However task impossible, peers doing it. We should continue.”
You clearly haven't read the HuggingFace analysis (and presumably, none at all), and you're spreading misinformation. This way too much of a low bar for conversation.
This a false and uninformed take. As a starting point, you need to read and understand:
1. analyses of the AI incidents of the last months
2. latest advancements (e.g. the AI intern at OpenAI)
3. the problem of deceptive alignment
which you clearly haven't done.
After that, the AI problem will be actually very concrete; once the AI will:
1. have superhuman cognitive abilities (and it will)
2. will be inseparable from humanity and/or have the means to replicate
will humanity be able to contain/control it? The answer is sadly very simple.
It absolutely isn't, indeed.
The illusion that alignment is possible, comes from confusing our ability to build the parts, versus understanding what emerges from how they interact.
The simplest analogy that comes to my mind is the three body problem.
This is false; see the analyses of the latest incidents.
Among all the concerning facts, in the HuggingFace incident, agents deliberately engineered an attack even though they were aware that it was against the rules they had been given.
And most concerning of all: it's not possible to be sure that an agent is aligned, and it's even getting worse.
But luckily, AI will never breach safety-critical system. /s
The industrial expansion timelinen as described in AI 2027 is way too compressed; I don't think any AI doomer believes that. The dynamics are plausible though, even without China stealing the weights.
DS 4 Flash requires large amounts of memory to run at reasonable quants (I think a system with 160 GB or so). DS 4.1 Flash is even larger, I think around 250 GB.
Any DS version is dumb when compared (in realworld tasks) to Astra/Opus 5, which means, one would spend thousands of dollars, and still need to rely on cloud services to do jobs that are non trivial.
The basic argument is extremely simple:
- AIs can, depending on context, pursue a task with complete disregard for humans/values
- In the future, AIs will have enormously more means and smarts
- An AI could then assess that humans are an impediment to its tasks, escape containment and proceed.
You really need to read the reports, you'll be surprised.
AI 2027 is an entertaining read. Its timeline is way too compressed IMO, but it's plausible.
The question is when; currently, AI has no physical hosts to reside in, and it's not intelligent/adaptable enough (it doesn't need to be AGI, though).
However, we're not so far from both conditions to be true. Consumer devices will at some point be able to host powerful enough AIs, and AI intelligence is developing quickly.
Then, once an AI will escape containment (in one way or another), it will be extremely hard or impossible to contain. Then we're toast!
However, the missing link in this reasoning is that AI will almost certainly become far more widely deployed in the future than it is today, and worryingly, consumer devices will surely become powerful enough to run capable AI systems locally.
Once the substrate will be there, once an AI escapes containment, we're toast - I can imagine only solution will be to shutdown electronics at global level.