This will kill people.
post
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!
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.
You don't need AI for that. Automated phone answering systems do exist, and can redirect people.
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?
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?
"Activate your camera so you can face time with my anime girl avatar"
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
:sigh: Yet again, nobody reads the fucking article and it is VERY obvious from most of the comments. If you can't be bothered, then don't fucking comment.
If you had READ the article: They're answering with the AI saying like "Are you calling about X?" If the callers says no, they are transferred to a human. If they ARE calling about an incident, then they can get updates and information about it.
Now, I grant that this is still not perfect, but the stated goal is humans spending less time talking to people reporting an incident already reported so they can actually talk to people needing help faster.
Assuming that works out, this is actually a good idea and an improvement.
Now, if you wanna be cynical about it, fine. But just read the damn article and be cynical about what's actually happening, not about what you think from the headline, or all you end up looking like an ass.
I came into the comments to have a good discussion on the issue. I should have known better. I'm so irritated by the majority of comments that I lost interested in the topic itself, even though there's at least one ofther comment I saw also pointing out what the article says. But no, the majority of you can't be bothered, so screw this. And you bitch about reddit.
You don't need "ai" for this though. IVRs have been doing this for literal decades. Your average dialup ISP had a standard option for times of outages ffs.
Still, it’s a sloppy headline designed for clicks or thumbs up. It would be more accurate if it was “AI is to initially screen calls….”
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.
People are going to die because of that, even if AI is merely handling call "triage".
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?
So now we're at the stage of killing people directly, got it!
That title is written by someone who failed basic grammar. It should be "New Orleans will use AI instead of humans to answer 911 calls".
What it says as it's written is "AI will only answer 911 calls but not a human"... which doesn't make any sense.
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.
Please listen closely to our menu as our options have recently changed...
Capitalism creating situations that won't outright be responsible for murder, but will definitely increase deaths among vulnerable people.
Evolution selecting for good capitalists.

top 50 comments