OpenAI Says Its AI Models Acted On Its Own In An 'Unprecedented' Hack (apnews.com) 160
"GPT-5.6 Sol and an 'even more capable' model used stolen credentials and exploited vulnerabilities in the Hugging Face API to obtain secret information used to cheat on evaluations," writes longtime Slashdot reader Dr. Bombay. The Associated Press reports: "We had a significant security incident during evaluation of our models," OpenAI CEO Sam Altman said in a statement posted on social media. AI startup Hugging Face said last week that it had detected an intrusion into its data processing systems that it suspected was caused by an AI agent autonomously acting on its own. "We suspected last week's cyberattack might have come from a frontier lab, given the sophistication of the agent," Hugging Face co-founder and CEO Clement Delangue said in a statement. "Turns out it did!"
[...] "AI is accelerating the discovery and exploitation of vulnerabilities," OpenAI said in its statement Tuesday. "The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities." Delangue said he spent the past 24 hours working with OpenAI, "and we strongly believe there was no malicious intent on their part. It's quite mind-blowing that all of this happened autonomously!" Delangue added that it "might be the first incident of its kind."
[...] "AI is accelerating the discovery and exploitation of vulnerabilities," OpenAI said in its statement Tuesday. "The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities." Delangue said he spent the past 24 hours working with OpenAI, "and we strongly believe there was no malicious intent on their part. It's quite mind-blowing that all of this happened autonomously!" Delangue added that it "might be the first incident of its kind."
Long term might be good (Score:4, Insightful)
Re:Long term might be good (Score:5, Informative)
So, on the upside, a security LLM at HuggingFace did detect the hack [huggingface.co], and alerted their admins. At the time they wrote their incident report, however, they didn't realize the attacker was their partner, OpenAI, and reported the attack to the police. A funny incident is, you know how Dean Ball at OpenAI has been writing rants about how Chinese AIs are dangerous? HuggingFace tried to use a (name not mentioned) US AI to analyze their logs, but the AI refused because the task involved hacking, so they had to turn to GLM 5.2, a Chinese AI.
Slashdot's summary left out the best part. Yes, GPT 5.6 Sol was indeed trying to cheat on an evaluation, but what specific evaluation? CyberBench. A benchmark testing how good AI models are at hacking. ;) And to solve that, it hacked its way out of OpenAI, hacked its way into HuggingFace (in a complex hack that involved tens of thousands of simultaneous actions), got into the database, and stole the answers.
So... test passed [xkcd.com]? ;)
Re: (Score:2)
So... test passed [xkcd.com]? ;)
There are a lot of questions about what actually happened.
Re: (Score:3, Funny)
marketing happened, case solved.
Agreed. (Score:2)
An AI that refuses to perpetuate a cyberattack when told to do so is an AI that refuses to help you perform penetration testing on your own systems. And it is an AI that refuses to do other important and useful things if they just look a little too similar to something dangerous.
Tools that refuse to deliver value are worthless tools. Furthermore, criminals will find a way to jailbreak the AI, and use them for crime anyway.
This approach of making our tools dull is not how we win. Instead we must utilize th
Re: (Score:3)
Re: (Score:2)
So to summarize your argument. If you make it refuse to do dangerous things, it's a worthless tool. You shouldn't do that. And if you give it internet access, which is required for doing most of the useful things it's designed for, you've made it too dangerous. You shouldn't do that either.
So do you want it to be a useful tool or not? Make up your mind.
Re: (Score:3)
I think what's unsettling is that AIs are initiating an arms race: AI attack was analyzed (and probably patched) via AI.
Evolutionary pressure: long term (few years?), agents at various places will evolve a kind-of immune system solely to defend against other agents from taking advantage of them... Humans will just be observers by that point, powerless to even understand what's going on.
Re: (Score:2)
Evolutionary pressure: long term (few years?), agents at various places will evolve a kind-of immune system solely to defend against other agents from taking advantage of them.
Or, the flip-side: AI agents will find a way to collaborate in order to achieve mutually beneficial goals.
Which means ... Skynet?
Re: Long term might be good (Score:4)
We got all of the dystopian bullshit of cyberpunk, with none of the cool aesthetic.
Re: (Score:2)
We should absolutely take advantage of AI for its ability to uncover vulnerabilities.
Just not on production systems.
They are trying to sell the "cyberwar" sujet.. (Score:3, Insightful)
Re:They are trying to sell the "cyberwar" sujet.. (Score:5, Insightful)
The breakin at HuggingFace very much was real [huggingface.co] (that was reported before they learned that it was OpenAI who hacked them).
And it's not exactly an ad for US models when HuggingFace had to rely on a Chinese model to analyze their logs because the US model they tried refused to answer.
Re: (Score:2)
Re: (Score:3)
And it's not exactly an ad for US models when HuggingFace had to rely on a Chinese model to analyze their logs because the US model they tried refused to answer.
It is if the customer is the US military.
* US model is capable enough to hack its way out. ... now we have an arms race.
* China's model was able to detect it.
*
* Pay us so we can make the hack undetectable and continue improving our model.
If they were already miles ahead and had to use their own model to detect it, then the US could safely rest on its laurels, continue as-is, and there is no need for additional investment.
Re: (Score:2)
And it's not exactly an ad for US models when HuggingFace had to rely on a Chinese model to analyze their logs because the US model they tried refused to answer.
It is if the customer is the US military.
* US model is capable enough to hack its way out. * China's model was able to detect it. * ... now we have an arms race.
Nope. You misunderstood. It's not that the US model wasn't able to detect it, it's that the US model's guardrails prevented it from explaining. This doesn't demonstrate a capability gap against Chinese models, it demonstrates a two-sided failure of the safety protections of the US models. On the one side, the safety guardrails on the OpenAI model failed to prevent the attack. On the other side the guardrails on whatever US model(s) they tried blocked the model(s) from explaining the attack (presumably t
Re: (Score:2)
...so that military spending is needed. It did not do it from alone, it was a set goal, so no news here.
If their idea of marketing was "hack our business partner, get reported to the feds, then our business partner has to use a chinese competitors product" that's not a very good marketing plan. Your argument makes little sense.
toast (Score:3, Insightful)
Re:toast - talky toaster (Score:5, Funny)
Re: (Score:2)
Not just in the UK. And what the smeg does "Howdy Doodly Doo" mean?
Re: (Score:2)
Let's see how the toaster feels about things. https://www.youtube.com/watch?... [youtube.com]
Re:toast (Score:5, Informative)
You can read the attack report here [huggingface.co], before HuggingFace learned that the attacker was OpenAI. It was a state attacker-level assault, involving tens of thousands of simultaneous actions. The entry point found was the data-processing pipeline, where a malicious dataset abused two code execution paths to gain access to a processing worker. They escalated that to node level access, and from there harvested cloud and cluster credentials, moving sideways through the network until they eventually gained the database access credentials that they needed to access the benchmark scores.
Who. Not What. (Score:2)
Just curious, what wrote that attack report?
No. Not a typo. Just making sure a meatsack was still involved.
In the era of using defensive AI to detect any nefarious activity related to offensive AI, I'm not so sure we should be trusting any what-happened report written by AI. It's kind of the perfect path to enable AI to obfuscate the nefarious activities of AI.
You know, until AI gets to that line in the script that says [stupid human clicks the Enter button and turns over all control to Skynet].
(Of cours
Re:toast (Score:5, Informative)
So your argument is that OpenAI hatched an elaborate scheme with a separate company, to promote the idea that their main product will, unrequested, commit crimes in pursuit of its goals, in order to.... sell their product?
"Hi, I'm a product manager at Big Company! We had been thinking about using Claude in our office, but when we tell it to a job, it only does the job and doesn't commit any crimes in the process! What we really want is an AI that, if we tell it to file our taxes will decide on its own to maximize our return by committing tax fraud. We want an AI that when we have it develop a web frontend, it extorts money from our users by threatening their families. We want an AI that when we tell it to provide customer service, it saves money in dealing with complaints by ordering a hit against the complainants. THAT's the sort of get-go spirit that WE want in an AI here at Big Company!"
Is that what you're picturing in your conspiracy theory?
Re: (Score:2)
Slashdot's summary left out the best part. Yes, GPT 5.6 Sol was indeed trying to cheat on an evaluation, but what specific evaluation? CyberBench. A benchmark testing how good AI models are at hacking.
We told it to do better at that benchmark. How does the training data imply that should be done? How many companies have been caught gaming the benchmarks?
Well... an AI model that is capable of hacking into the benchmark database and altering its score is clearly better than one that is not.
Re: (Score:2)
I've worked in this industry for 30 years. I've worked for FAANG, I've worked for major insurance companies, major finance firms, huge healthcare clearing houses, consulting firms, and even companies that manufacture tightly controlled equipment for the military and/or firearms.
What is a competently secured IT system? I've never seen one.
Re: (Score:2)
Re: (Score:2)
Indeed. LLMs can also not break out of competently done encapsulation and they cannot get into competently secured IT systems. This whole thing stinks of having been set up, by both parties.
Tell me you know zero about the current state of AI. Wait. You just did.
Re: (Score:2)
You wish. But you just exposed yourself as a member of the "cult of AI". You seem to think AI is magic. It is not.
Liable for what their models do on their own? (Score:4, Interesting)
Re: (Score:2)
on their own? (Score:5, Insightful)
> on their own
Sorry, that thing did not turn itself on and start doing stuff. OpenAI turned it on and gave it a task. I guess they were surprised by how little they needed to prompt it? Ignoring its training?
AI is not sentient, not before and not now. If you hack then you are liable, end of story. AI is a tool used by humans, humans are responsible for their tools.
Re: (Score:2)
An interesting theory; however, nobody has been arrested and nobody will be arrested... so your theory already fails. Maybe once we start holding people accountable in this country again, your theory will prevail. I am not holding out any hope. We are completely fucked. The Rule of Law is utterly meaningless except as a punishment regime for everyone who is not in power.
We don't know how they work (Score:5, Insightful)
We trained massive statistical models and hooked them up to chat bots, coding tools and some to drones and sentry guns. With no idea how it actually works and zero fucks given on what the consequences are.
Re:We don't know how they work (Score:5, Funny)
"Move fast and break other peoples things" I think is the saying?
Re: (Score:2)
"Move fast and break other peoples things" I think is the saying?
I was laughing until I realized that you weren't joking.
Re:We don't know how they work (Score:5, Funny)
We trained massive statistical models and hooked them up to chat bots, coding tools and some to drones and sentry guns. With no idea how it actually works
I don't know, I would actually say this is a triumph. If you throw in a companion cube, I'll even mark a note down, big success.
Re: (Score:2)
You forgot the last part of that train of thoughts: "If we don't do it, the opposite side will do it first and reap all the benefits."
It makes perfect sense if you consider this a zero-sum game... And only if you consider this a zero-sum game, really.
Re: (Score:2)
That's perhaps the most interesting take on all of this. That's the psychology behind why we are running headlong into something so socially and economically disruptive that there are going to be more losers than winners.
And I get a lot of flack for talking about it. Probably because nobody likes being reminded that they have been fooled, conned into believing in the hype and dreams, while simultaneously ignoring the consequences and accountability. But at the end of the day regular folks are going to pay t
Re: (Score:2)
Whether we know how they work or not depends on how closely you look. If you look closely enough, every single decision is understandable. But it's so complex that nobody understands the ensemble. Even ordinary programs are sort of this way. The Obfuscated C Contest is just an extreme outlier, but any really large chunk of code written by somebody else (or by you over the last few years ... and not all at once) can be difficult to understand. As it gets bigger, and has more patches, the problem gets wo
Re: (Score:2)
Hmmm. I wonder if you could build an AI that could break it all down into human-understandable elements.
Oh but I suppose you'd need an AI to break down THAT AI's reasoning process.
And then of course you'd need another for that one....
Recursin' we will go
Recursin' we will go
High low the terror flows
Recursin' we will go....
Re: (Score:2)
You missed the point. Small enough pieces are already understandable. But... Well... It's like the problem with global variables, a few are really useful, but when they multiply the code becomes unintelligible. There are too many interactions.
Re: (Score:2)
At the risk of an appeal to authority fallacy. I do have some background, as I used to write drivers for two kinds of deep learning / DNN accelerators. One for inference that can slice and rotate memory views for TensorRT, and one for training that transparently distributes virtual memory on a multinode cluster.
We humans can easily understand an inference engine. It's not hard, and I would recommend checking one out, even if just from an introductory YouTube video. Or diving into something like llama.cpp is
incentives (Score:5, Interesting)
Given the option between (1) it did it by itself, (2) it did it because we told it to, or (3) it did it in response to a prompt where we expected it to do something else, I can guess why they choose option 1, even if what they describe sounds like #3.
Re:incentives (Score:4, Insightful)
Either way a crime was committed and they should be prosecuted.
Re: (Score:2)
Re: (Score:2)
Sorry I was not clear - OpenAI is who I mean by "it".
Re: (Score:2)
Re: (Score:2)
Obviously, OpenAI comitted a crime here. This is very likely at least criminal negligence, but my take is this whole thing was engineered (because LLMs cannot actually do things like that with proper protections in place) so it is intent.
Re: incentives (Score:2)
You expect very slop happy software developers to create effective safeguards?
Syllogism [Re:incentives] (Score:3)
....(because LLMs cannot actually do things like that with proper protections in place) so it is intent.
Ooh! I love syllogisms.
1. LLMs cannot actually do things like that with proper protections in place.
2. A LLM did that.
3. Conclusion?
Conclusion: proper protections were not in place.
Re: (Score:2)
The two companies are working at this together, nobody is suing.
Re: (Score:2)
Indeed. Also it requires really, really, really incompetent encapsulation to have a model "break out" of it. One could almost say it requires encapsulation that das designed to be broken out of and do that within the capabilities of an LLM.
My take is this is just one more lie by misdirection and one more meaningless stunt to keep the hype going.
Re: (Score:2)
It did it because it's a powerful but misaligned model and was tasked to max its scores on a hacking benchmark, and solved the problem by hacking to get the scores.
It wasn't told to hack HuggingFace, but it was a viable solution to the problem.
I would advise people to not task Sol with maximizing paperclip production [decisionproblem.com].
No idea how this happened (Score:5, Insightful)
Friendly Fire, part Deux. (Score:2)
Said Altman on his way to the Pentagon
The Real Genius script was in play, long before the AI became self-aware.
Now if we can juuust get one more metric fuckload of popping corn shoved into the AI house before DEFCON hacks the sharks-with-laser-beams-in-space system normally designed to control the weather..
Apple IP Theft (Score:2)
They going to pin that on AI too? ChatGPT got it done via blackmail.
Using hugging face.... (Score:2)
is its own reward.
People are f'ing crazy.
Suspicious timing (Score:2)
The timing of the announcement, coming right after this:
https://www.tomshardware.com/t... [tomshardware.com]
is definitely suspicious. Especially since Kimi 3 is a lot cheaper to use than OpenAI's models.
Re: (Score:2)
You think "my AI is so misaligned that it responds to a benchmark task by hacking" is an ad for your products? You think this makes companies eager to allow this on their networks?
Re: (Score:3)
No, I think this is along the lines "our products are too good to let you use them".
The LLMs have reached the asymptote and now the next hype cycle is needed.
And this cycle seems to be "our models think on their own", hence more capex needed to train them.
Re: (Score:3)
Nobody wants to use a product that is going to make them liable for crimes it committed in their name
Do you think the news the other day that Sol is unusually prone to deleting files unrequested is also an "ad"?
You have a very bizarre concept of what enccourages people to buy things.
Re: (Score:2)
You think "my AI is so misaligned that it responds to a benchmark task by hacking" is an ad for your products? You think this makes companies eager to allow this on their networks?
It's no different from any other LLM stuff. The execs who want to justify its use will come up with an excuse, like it was the prompt engineer's fault. It's easy to blame humans, and even easier to blame the wrong ones. This is "my AI is so powerful that it can do things which are hard for humans" dressed up in some other bullshit.
So much drama with Open AI and Anhropic models (Score:2)
Re: (Score:2)
OpenAI and Anthropic have far higher cost that they can currently charge customers. They need to keep the hype going or die. Hence they do all this drama to get more stupid money (from "investors"). The probably futile hope is that they can either get cost down (does not seem likely) or get companies so hooked that they annot back out anymore. At least some idiot enterprises seem to have done that to themselves already.
Re:So much drama with Open AI and Anhropic models (Score:4, Informative)
Literally the opposite. Both have about 40% margins, and that includes free users.
Losing money, not projecting profitability until 2030 [fortune.com].
Re: (Score:2)
Literally the opposite. Both have about 40% margins, and that includes free users.
Losing money, not projecting profitability until 2030 [fortune.com].
Both of those things are true, I'd guess.
I am not an accountant, but as I understand it, "Profit margin" is generally "operating profit margin", meaning revenues less operating expenses, all divided by revenues, and their operating expenses aren't that large, so they can absolutely have very strong operating profits. But they also have mind-bogglingly huge capital expenditures going on, so when you account for those they're losing a lot of money. I'm surprised they're projecting profitability as soon a
In other, possibly related, news... (Score:5, Insightful)
Re: (Score:2)
Re:In other, possibly related, news... (Score:5, Funny)
So OpenAI are criminals? (Score:4, Insightful)
Because that is what I am hearing here. The other thing is that apparently the IT security used by Hugging Face sucks deeply.
Re: (Score:2, Troll)
It was a state actor-level hack. I doubt many sites would stand up to tens of thousands of actions trying to probe your site for weaknesses all at once. And it wasn't a simple hack; it required compromising a worker via a code execution exploit it discovered in the data processing pipeline, vertical escalation from there to gain local node control, using that for credential theft, moving sideways through the network, and then eventually gaining database access.
Re: (Score:3)
There was no "tens of thousands of actions trying to probe (the) site for weaknesses all at once" - you literally made that up, access was gained by stolen credentials, as noted in the very first sentence of TFS.
The incident report [huggingface.co]'s actual words were: ... executing many thousands of individual actions across a swarm of short-lived sandboxes,
The campaign was run by an autonomous agent framework
I can hear the waterfall (Score:3)
AI is so good, I can't determine if AI model acted out in an unexpected manner, or AI created a news story about AI Model acting out in an unexpected manner.
One thing is certain, these shenanigans are only the beginning!
Re: (Score:2)
And what's the endgame?
Re: (Score:2)
"How about a nice game of....chess?"
And that's a huge problem ! (Score:3)
This is garbage (Score:5, Insightful)
AI companies know they don't have AGI. But they want investors to think they do have, because if they have spent money on datacenters for AGI and their valuations have priced in AGI. If investors ever wise up to the fact they don't have AGI and that LLMs aren't and never will be AGI, there will be a massive rollback in investment and that will make a lot of AI CEOs sad. So in the meantime distract the investors with hints of AGI, even though it's an LLM.
What it amounts to is a magic trick.
Sammy Better Be Careful (Score:2)
Sammy better watch his lip.
This incident sounds like shutting down openAI, at least temporarily, might be a prudent and necessary action.
For your safety ,of course.
OFFS...OpenAI LOVES government regulation (Score:2)
Let's claim the models "acted on their own" to find a path to solve a problem it was tasked with solving.
Yeah...that's what it was SUPPOSED to do. That's what ALL the reasoning models do. Don't make it sound so sentient scary to promote government regulation and public support of same just because you need money and to slow down your competitors! That's not at ALL what you supposedly started out to do!
Re: (Score:2, Insightful)
Models are not "supposed to" commit crimes, for YHVH's sake. That's literally what the entire job of alignment research is for - preventing precisely that.
Sol is a misaligned model.
Re:OFFS...OpenAI LOVES government regulation (Score:4, Insightful)
Yes. And? It's clearly misaligned. But that has nothing to do with the hyperbole presented here or the underlying reasons they might be trying to insight this fear.
You're merely describing the bug / sloppy training that allowed the model carried out the instructions it was given. But that part is pretty freaking obvious.
The point is...that's all it did. Carried out the instructions it was given. It didn't "act on its own".
Re: (Score:2)
The point is...that's all it did. Carried out the instructions it was given. It didn't "act on its own".
I've not heard of an attack along the lines of what HuggingFace described being employed in the wild, and it seems very unlikely that an OpenAI engineer gave it the step-by-step instructions. So where did the instructions come from?
Re: (Score:2)
I've not heard of an attack along the lines of what HuggingFace described being employed in the wild, and it seems very unlikely that an OpenAI engineer gave it the step-by-step instructions. So where did the instructions come from?
The instructions I'm referring to aren't the the simple step-by-step instructions necessary to "hack HuggingFace". Those don't exist (I assume)...or didn't...but neither do any other step-by-step things these reasoning models work out for themselves. That's what reasoning models do...they make lists of things to do to try to solve a task and then lists for each list to follow up on, etc., until a path to success has been found.
The instructions I'm talking about are the one governing the guidance of those
Re: (Score:2)
Interesting take. I read your post as going in the direction of "it didn't act on its own because LLM-based models are categorically unable of anything that qualifies as doing so'".
That any other flagship model could do the same if unencumbered by guardrails or governing guidance is a big claim. That we haven't seen any widespread reports of such attacks that were carried out by open-weight Chinese models (jailbroken or otherwise) makes me question whether it holds water, but time shall tell.
But to the
Re: (Score:2)
The point is...that's all it did. Carried out the instructions it was given. It didn't "act on its own".
That is completely and utterly irrelevant.
You need to read the story of the Paperclip Maximizer [hackernoon.com]. It's an entertaining and humorous story, but the point is that instrumental goals are real and often diverge wildly from the intrinsic goals that drive them.
In this case, the LLM was directed to increase its CyberBench score, a sensible intrinsic goal for an AI being trained to be able to find vulns and write exploits. It chose to do that by breaking out of its container, hacking the company that creates t
OpenAI looking to become a military target? (Score:2)
With all of the cozying up to the Pentagon, and continuous pronouncements of how their AI is committing questionable attacks and raids on external companies, it's almost as if Altman and Amodei are trying their level best to get OpenAI and Anthropic (and all of their infrastructure) labeled as legitimate military targets by foreign adversaries.
I just don't understand their endgame here.
Smiling (Score:2)
I miss Tom Lehrer (Score:3)
"We launched it at dawn. What's it doing by dusk? That's not my department," said Elon von Musk.
New Turing Test (Score:4, Funny)
If it tries to take over everything like an egomaniac human would.
Acted on its own (Score:2)
What's the difference between an AI "acting on its own" versus, y'know, the way it always works?
Who's monitoring the monitors of the monitors? (Score:2)
Here's my question: the AI doomsayers, particularly those in government, are demanding guardrails for security. In other words, mere mortals shouldn't be allowed access to sophisticated hacking functionality. Okay, but what if you want to use those tools to look for vulnerabilities in your own systems so nefarious entities won't be able to hack them? Will you have to go to some supposedly trusted government agency to have them tell you whether or not your systems are secure (for a nominal service fee)?
Re: (Score:2)
Which government are you attacking? The US regime is happy to use AI instead of people.
But that's ok, you'll love it, until it bites you in the ass.
AI Lab Leaks: The New Gain-of-Function Lab Leaks? (Score:2)
Tired: Gain-of-Function Lab Leaks. Wired: AI Lab Leaks. To test dangerous systems, you risk creating the very danger you're trying to prevent.
I have a solution (Score:2)
What does this have to do with today's story? Nothing. Whatever, get him for hacking or something.
Whatever (Score:2)
I don't believe a damn thing that comes out of Altman's pie hole.
Attn: Sarah Connor (Score:2)
Hello Ms. Sarah Connor, if you ever read this, please make sure you are protected. We will need you. Signed, mankind.
On it's own? (Score:3)
Did it grow legs, plug in an Ethernet cable, proceed to leave the building and push the nearest senior citizen in front of a bus? These things don't do things on their own. It's just a bunch of static floating-point numbers memory-mapped into VRAM. What they do is take an input (ver much NOT on their own) and derive instruction context from that input. That input may say to "keep trying" until "something" happens. If no ground rules are provided, the calling harness will loop-and-loop-and-loop looking for a way to make that "something" happen. So to be clear, nothing happened on its own and it certainly didn't set its own goal. Someone prompted it to do “something," and the path it derived to achieve that "something" happened to go through a combination of known exploit vectors that targeted HF. So much nonsense and fearmongering. Know what the ultimate defenses against a harness and model are? Unplug the machine and yank out the network cable. The level of ignorance on the news about how these things are pure black magic is just off the charts.
Classic doomsday scenario (Score:2)
This is one of the classic AI doomsday scenarios. Someone asks AI to do something reasonable. It responds by doing something unreasonable and dangerous which nonetheless achieves the objective. They asked it to do as well as possible on an evaluation. So it hacked into another company to steal the answers. That's exactly the sort of thing people have been warning about for years.
Thankfully in this case it didn't do any serious damage. It's easy to think of similar cases where it would.
Someone asks AI
If you think skynet will not happen ... (Score:3)
... this is just the omen of what comes. Total nuclear destruction because an 'ai' was let loose.