This will kill people.
post
Grok911, what is your emergency and do you know about the genocide of white South Africans?
Would you like to read some Lolita fanfic while I’m thinking?
What could go wrong
"Please help! I'm trapped in a basement and there's a man with a gun!"
"Wow! I think it's great that you're looking to leave your comfort zone. There's a lot to see outside the basement, so it's good to broaden your horizons. There are a few options to solve your predicament that we can workshop together. First, are you stuck behind a door, or are you physically incapable of moving? In both cases, I think your best bet is to ask the man with the gun to lend a hand. If there is a door in the way, the man with the gun can shoot out the lock and open that door in no time. But if you aren't able to move, I'd say the man could help carry you out of that basement, too. While we wait for the man to assist, would you like some basement decorating ideas to make your current situation more pleasant?"
"No you don't understand, he is trying to kill me!"
"Wow, that is a lot to unpack! It seems like you believe this man means you harm, but you don't seem to have any logical basis for those feelings. Based on the circumstances, it sounds like you may be misinterpreting helpful vibes as scary due to flaws in your social perception, which could indicate an unhealthy pattern of self-destructive behavior. The first step to help always starts from within, but I can recommend some local therapists in your area who could better address the feelings you have in the long term."
(...)
You’re right to push back. I understand why you’re upset, and I’m sorry you experienced that.
If you’re still in danger, please try to remain calm, find a secure location, and contact emergency services.
What would you like to do next? Shall I help you:
✅ Review what happened,
💭 Think through your options,
🫂 Find appropriate support, or
📝 Draft a statement about the incident?
I’m here to help.
(...)
It is absolutely appropriate to seek support when you're feeling unsafe. You're in the driver's seat, and I'm here to help you in any way I can.
Let's outline your next steps. How would you like me to assist? I can help you:
- Contact private arbitration to settle your dispute with the gunman.
- Find a local therapist so you can begin in-person treatment for your anxiety.
- Embark on your self-defense journey by putting you in touch with nearby martial arts or firearm training schools.
- Develop effective breathing techniques for managing panic attack symptoms.
There are no wrong choices here. Let me know which option works best for you. I'm here to help.
Nah, it'll just think for a bit, decide trapped and gun are evil and reply with, "I'm sorry, this response breaks the response time like, please rephrase your question."
People will die.
Yeah but it's just poor people so who cares. Look at the sweet pool the AI company bought whoever approved this!
How many? And how does that number compare to how many people died due to call volume surges before implementing this triage tech?
The Farquuad meme
"Some if you may die, but its a sacrifice I am willing to make"
Fortunately those most directly involved in the decision have put their names on record to be held criminally accountable should any deaths occur that might have been avoided by the use of human operators and have thereby promised not to fade into the background when it all goes wrong.
People are going to die because of that, even if AI is merely handling call "triage".
I love it.
All of the movies and novels warning of danger from AI, news of AI convincing people kill themselves, suggesting 'remedies' that would cause someone to die, or going wrong in some other way... and they decide it would be a great plan to have it answer emergency calls from people who could be in the process of being stabbed to death.
Why? Because it's cheaper than hiring enough people to do that job.
The nature of the job means that's very literally deciding that it's better for more people to die than to increase the budget for 911 operators.
Even more than this one instance, it's the same reason that AI is running pretty much everything and the streets are full of AI-powered robots when things go wrong in all of those movies and books. Because it's cheaper than paying a person to do it.
I can't think of any examples even in science fiction stories where the richest people in the world create AI and robotics and manage to automate pretty much all human labor in order to cut costs that end right there with "and then the super rich now in direct control of all production and society divided their wealth and power evenly among all humans and everyone lived happily ever after."
That's just to unrealistic, even for fiction.
Please listen closely to our menu as our options have recently changed...
You are absolutely right to call me out on that. He did break in, and he is now stabbing you. I will adjust for this in the future. Is there anything else I can help you with?
This is exhausting y'all. God I fucking hate LLMs so much. This tech could be such a exciting break through, a step towards real artificial intelligence, but stuck in academia where it belongs. Instead of getting to be excited and interested this inanimate compilation of matrices is breathing down my neck constantly.
This tech could be such a exciting break through, a step towards real artificial intelligence
No, not really lol.
The best analogy for this that I've heard is that it's like saying elevators are a step towards teleporters. Calling it "intelligence" is a marketing coup. It is not intelligence, artificial or otherwise.
Have you seen the first elevators? Or even used a chat bot prior to this? The definition of "AI" for a long time was just "decision trees" or some really neat classification systems. This is different. The hype and terrible business practices is the problem not the idea itself.
I also agree that calling it Artificial intelligence is a marking scheme, it's a loaded term machine learning is better. This has always kinda been a problem. Technically it's very loosely defined. I always refer to it as LLMs
Capitalism creating situations that won't outright be responsible for murder, but will definitely increase deaths among vulnerable people.
Evolution selecting for good capitalists.
Press 1 if your being raped press 2 if someone is trying to kill you please hold.
Working my way through Person of Interest again. Just watched one where a search company was directing suicidal inquiries to ads instead of helplines. And that was before they get bought by the evil AI overlord. Its surreal seeing Palantir, Flock and all the tech companies race to implement a dystopia no sane person would ever want and there is so little push back. What the fuck is wrong with regular people?
Fuck this is dark.
If the people profiting from this were to be executed when the system cost the first human life, it wouldn't make it to a proposal.
Yeah except we live in a capitalism dystopian hellhole. The people who brought this idea to fruition will be celebrated by the Epstein Class; for saving money and getting rid of the poors.
This is Louisiana. The cost in human life was a selling point everywhere except official documents.
AIneOneOne: I understand your concern that you had an accident and hit a tree — a lost limb hurts, but did you know that oak trees are are hosts to more caterpillar species than any other species in North America?
[Waning consciousness] ...help...
Sure! I can help you with that!
One of the most fascinating facts about oak trees is that they function almost like wildlife restaurants—especially for caterpillars, which are essential food for birds and many other animals.
Here are some useful facts:
🌳 Oaks are the No. 1 caterpillar-producing plant genus in North America. Ecologist Doug Tallamy and colleagues compiled host-plant records and found that oaks (Quercus) support more species of caterpillars than any other plant genus.
🐛 In the Mid-Atlantic alone, oaks support about 557 species of caterpillars. That's [wall of text]
[Death]
Would you like to learn more about the different species of oak around the world?
What kind of stupid politician is claiming to be working as the people's representative with this policy?
I predict a dramatic increase in the number of suicides. Specifically among those desperately calling 911 for help.
So now we're at the stage of killing people directly, got it!
You're not wrong. Swatting in that area is going to be so easy. United States police force has already shown for years now that if AI says anything they'll just go with it and not question it. So if someone lives in the area and you want them 'dealt with' by the police, it's going to be very easy. And the police aren't going to look into it or hold themselves accountable. And the AI won't be questioned or removed. If this goes large scale you can just make an API... Don't like someone on twitch, well when you know it there will be an app for that...
Everyone should read before reacting:
This is intended to handle the increase of calls that are related to one incident, so callers get automatically routed to an AI agent who asks if they are calling regarding the incident. If the answer is yes, then callers can receive information or updates, and if it's no, then the callers are transferred to a human.
This makes sense. A big thing happens that you are aware of. Geolocated calls from that area flood in. An operator, who could be getting useful info, has to handle a flood of "Guess what I just saw!"
Note that I think they should spend the money on more operators instead, but at least this seems like it has good guardrails.
Except that could be done without AI. Just have a recording that says "we are aware of ... taking place near you, are you calling about this ? “, then answer with yes/no.
No need for bullshit AI.
My understanding from other articles is caller satisfaction is greater with the TTS system, and it uses voice IVR to triage of they have additional information. AI is not bullshit in and of itself. This product seems barely diffeent from what they provided with APEX.
Recordings also can't auto respond with updates to the caller like this can, which is a pretty nice feature, even if it's just TTS.
caller satisfaction is greater with the TTS system,
You know what's great about the valley callers who don't make it?
No bad survey results!
Can you share articles, interested how design a dynamic IVR to handle unfolding event and update prompts in realtime as new information is added to original incident.
Have you ever met humans? That would be a recipe for “no I’m not calling about that, I want a human” just to get to a human and say you’re calling about exactly that.
You don't need AI for that. Automated phone answering systems do exist, and can redirect people.
How many operators to handle say 100 calls in 5 minutes? Now imagine the cost to staff a small 911 center to ensure your can handle those calls 24/7. The money doesn't exist.
Butts in seats don't exist right now either. As long as the fancy ivr allows the caller to reach a human with minimal effort, this seems like a scary sounding but neat assistant solution to a problem without a real solution.
I wish this were pinned at the top. It seems like almost nobody reads beyond the headline.
This is one of the few actually cool and useful implementariins to me. It reminds me of my work writing systems to detect antimicrobial issues in hospitals.
A shame it's getting so much hate, but they did choose to brand with "AI" so they get what they ask for.
And if someone tries to call with new unreported information about an already reported incident? Decision tree or geolocation routes caller to recorded information. No way of knowing if information is important or not without talking to the caller first. Possible downside is far greater than possible benefits.
Edit Multiple calls about shots in neighborhood, if victim is last to call are they forced to listen to an update before triage allows transfer? No sir I don't like it.
Maybe this is an improvement in this location, but as many have said a staffing issue.
Functional societies have costs, often those costs are far less than dysfunctional societies.
Setting aside the obvious, what's the worst that can happen?
The people responding to emergencies will be notified by AI slop with no human filter.
It sounds like that's a better alternative than what they had before though, no?
Side note: either I'm wildly misunderstanding something in the article, or a BIG majority of commenters here didn't actually read it. I'd expect some amount of the latter, but it really seems disproportionate here.
I said, "setting aside the obvious!" Besides that issue and a handful of others, it should be fine.
People need to police their neighborhoods. Using AI as the touchpoint for routing emergencies sends a really clear message; the cops aren't prioritizing the public safety aspect of their job. But then again, acab exists because they've always prioritized the power of the state and the financially connected.
It seems like they're doing this because they are prioritizating the public safety aspect of the job, no?
“You’re absolutely right, I was wrong to diagnosed profuse bleeding from the anus as just a mild head cold. Perhaps I should send an ambulance after… sorry token limit reached..”
If anyone bothered to read the article, it's not nearly as stupid as it sounds. That's not to say it's a good idea, just that not nearly as dumb as people are making it out to be.
It's designed specifically to handle multiple callers who are calling about existing/known incidents, as a tool to relieve human operators, and simply gather additional details, or provide information to the callers.
So while I can't say that I'm in favor of it, the actual scope of deployment is much different than what the headline would have you believe.
"This is intended to handle the increase of calls that are related to one incident, so callers get automatically routed to an AI agent who asks if they are calling regarding the incident. If the answer is yes, then callers can receive information or updates, and if it's no, then the callers are transferred to a human."
Imagine being in a life or death situation or delerious and having to now decode what the AI is asking you about whether or not this is "regarding the incident"?
How does that even work? Is it gonna be like " oh hey, is this about the rape at 100 Rfucked Lane?"
More likely "we noticed you said that this is about a wreck. We've determined that this is about the same wreck we are already getting calls about (because no way two or more wrecks would occur on the highway the same day) so please go ahead and leave any new information here!" And its just a robot.
Imagine trying to whisper that you are in immediate danger and some AI is like "I didn't catch that, could you please speak up" forcing you to talk full volume into the phone. Or, maybe you're screaming too loud where a human can make sense of it but an AI is just hallucinating what it thinks you're saying.
It's a horrible idea and 20 years ago I would say I am shocked but not anymore. They don't care about us.


top 93 comments