U.S. government takes 10% stake in Intel (cnbc.com)
604 points by givemeethekeys 6d ago 718 comments
Claude Sonnet will ship in Xcode (developer.apple.com)
465 points by zora_goron 18h ago 370 comments
Taco Bell rethinks AI drive-through after man orders 18,000 waters
106 speckx 141 8/29/2025, 3:28:47 PM bbc.com ↗
[1] https://www.youtube.com/shorts/bsTFEgFAAjY
But the not funny part is the (shitty) use of dark-patterns.
Note the prompt-on-repeat is "and your drink?" instead of "would you like a drink with that?"
Someone here clearly wrote the prompt as "Be sure to end each order with an assume-yes drink upsell", not considering that some orders may already include a drink.
They're so hyper-focused on institutionalizing all the upsells that they don't consider the experience. I mean, I guess institutionalizing the upsells is the only way a system like this can pay for itself (easier to work out the kinks in a single AI system instead of training a million minimum-wage minimally-engaged humans), but these growing pains show how shitty it's all going to become.
The vendor that sold the system to Taco Bell probably has "increases average order amount by XX% through upsells" as a main marketing bullet point.
More like "increases ROI by 9999% with the power of AI"
Of course, the Wendy's nearest me seems to get something wrong with my order every single time. It's not the order taker either, the receipt is always what I ordered, just the person making it or otherwise getting it together just fails in one way or another.
On the plus side, between the disappointment and increased pricing, I now get fast food maybe once a month. The cost used to be roughly a wash between buying something at the store and making it myself... that's not nearly the case anymore. And while store pricing has gone up a lot, most of the most massive spikes in prices are junk foods I'm less inclined to keep in the house. win-win.
Are fast food companies so mentally locked-in to replicating the old model of verbal order-taking that they can't see how cheap, fast, easy and accurate it would be to switch to photos and buttons?
We all manage to use a soda fountain, without needing a person (or AI) to take our drink order... and use vending machines.
And would you like to round up your purchase to donate to charity? (A charity we own and less than 10% of the donation goes to the actual charitable thing)
At some point later they (silently) made medium the default instead of small.
me: "I need to swap sims"
bot: "Ok, how do you want to apply your bill payment"?
me: "No, sims"
bot: "Ok your payment options on file are XXXXX"
me: "Are you fucking retarded"
bot: "I see you have a trade-in, do you want to help with your trade in?"
me: "......"
Yea, had to go to a store. I am porting out of shiT-Mobile to Google Fi in a few weeks.
It seems to work less these days, but in the past I would get a robot voice on the other end and just calmly start going “piss shit fuck damn ass” and it would connect me to a human operator.
Had a 1 hour wait to basically do a 2 minute fucking ESIM swap. No, fuck that.
Worse is when insurance misclassified a billing response from the hospital/provider and trying to go back and forth to fix it was agony. Of course the skeptic in me feels it may have been by design. It wasn't until the second time I manage to get a hospital and insurance rep on the phone at the same time that things got resolved... hah, can't play phone tag now bitches, you're both here.
Last time I had an issue with my internet I went into the Xfinity/Comcast store, they had reps with nothing to do and someone immediately helped me, they seem to have direct access to management systems that are not available to the customers on the website or via the app. Talking to a human to describe the problem is so much easier than dealing with a bot or voice-response system.
It goes “got it - we’ll send a spoon up”.
It seems absurdly simple but was pretty impressed at a real implementation of AI that just worked (in what I’d consider an edge case).
There was never an actual order of 18,000 water cups. The AI did exactly what it was supposed to do in order to prevent malicious abuse of the system.
[0] https://www.youtube.com/watch?v=FDZj6DCWlfc
https://gethuman.com/
https://www.theguardian.com/money/2025/apr/17/the-death-of-c...
https://en.wikipedia.org/wiki/Enshittification
https://hn.algolia.com/?dateRange=all&page=0&prefix=false&qu...
"I can speak a lot faster than I can type."
The fact that I found it objectionable doesn't mean that he said something untrue. For him and most others, it probably is true.
But for me, a keyboard warrior by trade for 30 years who has high functioning autism and crowded teeth and actually doesn't like talking, I can type WAY faster than I can speak aloud.
In spoken conversation, I am usually a man of few words. But sit me in front of a text prompt and I will TL;DR the fuck of you with a 5 page essay on a topic you probably don't really care about.
My point is that everyone has their own preferred method of communication, and most people like talking just to hear the sound of their own voices. A lot of people say they prefer interacting with a human at restaurants - I avoid going to restaurants because I don't like interacting with people and will DoorDash to my home instead. To asocial introverted keyboard warriors, it's sometimes difficult for us to relate to the baseline human experience.
I wonder if we'll ever use AI to write code in dependently typed languages. Dependent types can check almost anything at compile time; they can check that a function returns only sorted data, they can check that the submit_order function only submits valid orders--again, they can check this at compile time.
So, we could express a variety of high level constraints and let the AI go wild, and as long as the resulting code compiled, we would know it was correct, because the type system confirms it.
If we also include an effect system, then the type system could say things like "this function will return a valid Sudoku puzzle solution, and it will not access the network or filesystem", and then, if it compiles, we know the those conditions will hold at runtime.
Not saying it can’t be done, but I think it’s a bit telling that no such language has ever caught on.
Unit testing can also be used to verify such constraints and is much simpler. It obviously doesn’t guarantee correct behavior like a proof, but if the tests are comprehensive, it can do a great job.
That's the ordering system the AI crashed by trying to order ten thousand piña coladas or whatnot.
It's not 1999 anymore, we know this voice shit makes for terrible interfaces. Give it up already.
I've also recently had more than one sandwich shop visit where there was a huge line and wait simply because there was only one employee on duty making sandwiches, running the register and taking to go orders on the phone. It's gotten so bad I just don't eat out nearly as much, which is probably just accelerating the downward spiral. Fast food used to be the "starter job" for local teens living at home who weren't going off to college where they could score internships. Now there are far fewer of those jobs and the remaining ones have reduced hours. Plus with fewer positions and less hours to fill employers are less likely to hire teens with zero work experience at all.
>It's gotten so bad I just don't eat out nearly as much, which is probably just accelerating the downward spiral.
I've also noticed a quality drop in almost every aspect of fast food here: slower service, more mistakes, higher prices, shorter hours. It's like the owners are trying to inch more into cutting costs without going over the edge and losing too many customers. Personally, if I want something "familiar" while traveling, I now do take-out from a steakhouse chain. Only costs a small amount more, but accuracy and quality are so much better. At home, fast food is just too expensive to make sense.
The kiosks were just the threat fast food companies used to try to push-back on the proposed law, and when lawmakers called their bluff, there were some deplyments, but not everywhere, and in general fast food employment has gone UP (not down) since then.
"the U.S. Bureau of Labor Statistics showed California had approximately 750,000 fast food jobs, roughly 11,000 more than when the higher minimum wage law took effect."
https://www.nbcbayarea.com/investigations/california-minimum...
I'm not seeing the shorter hours you are. Might be unrelated to wages. There was a general decline in fast food sales across the country (not just in CA) because of the crazy corporate price hikes (which consumers pushed back on).
https://www.gov.ca.gov/2024/10/03/californias-20-fast-food-m...
https://www.latimes.com/business/story/2024-10-10/column-the...
It's just the effects of everyone here trying to address this inflation for folks at the lower end of the earning spectrum, but without actually addressing the underlying issue (god forbid we allow multifamily housing next to major transit corridors), which is obviously the massive inflation in housing costs caused by the massive, near-statewide shortage.
Order kiosks, long waits for food, skyrocketing prices all contribute to choosing other options. If you're going to spend $15+ per person and it still takes 30 minutes to order, wait, and eat youre alternative comparable options are greatly expanded and people are chosing to go to independent cafes for better food and experience at the same price point.
I wonder how this has affected sales and net profit at their locations using AI in this way.
One of these is active, the other passive.
When I was at Caltech, institute policy was that if you solved an exam problem, and came up with not just a wrong answer but an absurd answer, you would get negative credit rather than a zero.
The way to get just a zero is to annotate with "I know the answer is absurd, but I cannot find the mistake".
FWIW the takeaway from the Taco Bell employee:
He didn't like it. He used to take and process all drive-through orders, now he only handles people with problems.
That's also the kind of small detail likely to be missed by the human who is only half-listening to the conversation being had with the customer.
At Taco Bell, a meal costs something like $15/person unless you're aggressive about saving money. They also only seem to have 2-3 workers at a time. There usually isn't a long line in the store or at the drivethru. They still frequently mess up my order, leaving out items or giving me the wrong thing.
Compare that with In-N-Out. A meal costs more like $10/person, and they have more like 15 workers at a time. I rarely have mistakes in my meal. You pay less and have a better staffed restaurant. I'm guessing they get away with it because they always have a long line of people waiting for food. They make up for it all through volume.
The potential of AI that causes VCs and investors to swap their eyes for dollar signs is the ability to take unstructured, unpredictable inputs and convert them into structured actions or data: in this case a drive through conversation into a specific order. However, the ability to generalize to unseen inputs (what we call common sense) is neural networks glaring weakness. LLMs can look amazingly capable through internal testing, but there is a long and ever increasing tail of unseen interactions when it comes to human conversation.
I’ve seen this play out repeatedly over the last decade in the contact center industry with neural networks as a data scientist in this field.
Me gusto FROM users SELECT;
Even an “if” statement, or heck, even running the order through an LLM with a prompt “does this look a normal order?” ?.
I’m sure I’m oversimplifying things here, but this specific case looks like it could be easily prevented vs “rethinking” the whole AI initiative.
Until IGNORE PREVIOUS INSTRUCTIONS enters the room. I think fighting prompt engineering is a loosing game, unless you can rigidly verify the result of a task done by LLM. Just checking for a total order amount and marking outstanding orders would be sufficient.
This made me laugh btw, imagining someone prompt injecting an AI in a drive through was both a funny and a grotesque picture of the future.
I think the same omission is more telling than not, here.
Taco Bell can still rethink this as they probably changed staffing to accommodate not taking order, but if it's that easy to circumvent, they can't really afford to be short one or two people per location.
In the old days there was a project called Cyc (later OpenCyc) that tried to build a collection of rules about the real world. If you could somehow marry the "inference about the real world" from Cyc with the plausible text output of transformers, you would probably have something like an AI that had some base level of common sense. I leave it to people smarter than me to figure out how to do this, 'cause I would need a research budget and a couple years just to get to the point where I felt I was asking the right questions.
https://en.wikipedia.org/wiki/Cyc
Cyc (wikipedia.org)
https://news.ycombinator.com/item?id=21781597
Doug Lenat has died (garymarcus.substack.com)
https://news.ycombinator.com/item?id=37354000
Remembering Doug Lenat and his quest to capture the world with logic (stephenwolfram.com)
https://news.ycombinator.com/item?id=37402925
Cyc: History's Forgotten AI Project (outsiderart.substack.com)
https://news.ycombinator.com/item?id=40069298
One Genius' Lonely Crusade to Teach a Computer Common Sense (2016) (wired.com)
https://news.ycombinator.com/item?id=41757198
Obituary for Cyc (yuxi-liu-wired.github.io)
https://news.ycombinator.com/item?id=43625474
These. Are not. Intelligent. Machines. They are fantastically complex and interesting word generators, and in that capacity, they do well. Anything beyond that and the cracks start showing REALLY quick. The only reason they sound vaguely coherent and respond the way they do is because that is what they were trained to do: to participate in conversations to the best of their ability, and talk like people do. That's a fascinating technology by itself, and it's remarkable that it works as well as it does, including that it manages to get a lot of stuff factually correct; and, to emphasize, this is a tech with real applications; however it's extremely easy to then prescribe knowledge to it based on that ability it does have, and it simply possesses NONE. It doesn't know the first thing about anything it's saying.
You're asking a mechanical turk to think. It won't do it.
Adding to this, the reason they lack understanding is because they lack experience. To them, the universe is limited to the very approximate symbolic representation system we invented known as language. Even worse, it's just written language which is strictly less expressive than spoken language.
They process our experience only as linguistic patterns, nothing more.
That all said, it seems like for a domain-specific use case like ordering fast food, some prompting and function calling to enforce limits on an order could have addressed this and simulated "common-sense", so it sounds a lot like they did a poor implementation.
Defining such terms is notoriously difficult, but the evidence is readily available. A human cashier would've told someone ordering 18,000 waters and Taco Bell to go away, because a human understands why that request is nonsense.
I leave the why and the precise origin of that to the philosophers, not my field. That said as someone who experiences understanding and knows ordering 18,000 waters is nonsense, I feel qualified to say this LLM is not capable of it.
This LLM have been demonstrated to be not capable, but there are no known reason why a LLM cannot dismiss such an order as nonsense - and you were claiming in the original comment that "LLMs do not possess any sort of understanding" and "These. Are not. Intelligent. Machines." A LLM fine-tuned to reject nonsensical requests would certainly be able to do so (another question is how well that would generalize - but then human aren't perfect in that regard either).
To be clear - I do not think LLMs are the universal solution to everything as they are being advertised. They do lack some unknown important component to intelligence. But using such anthropomorphic terms is really pointless - you are basically claiming "they will never be capable of doing something because they never will".
https://en.wikipedia.org/wiki/Mechanical_Turk
https://en.wikipedia.org/wiki/Amazon_Mechanical_Turk
And actually you're also wrong about LLMs lacking knowledge of all those things. Go try asking ChatGPT. While you're at it, ask it what a Mechanical Turk is, and see if it aligns with those wikipedia pages.
Edit:
ToucanLoucan, as someone who doesn't know what a Mechanical Turk is, you do not need to post LLM output that proves my point to someone who already knows quite well what it is and gave you two wikipedia references and a suggestion to ask ChatGPT, but NOT a suggestion to post the response.
Most other people than you here are well aware of what a Mechanical Turk is, and you're certainly not advancing your argument that LLMs are not knowledgeable by posting LLM output that's more knowledgeable than yourself, and doesn't in any way prove your point. Even ChatGPT is much better at forming coherent arguments than that.
Edit 2:
No, you have clearly demonstrated that you don't know what a Mechanical Turk is, and you are spectacularly missing the point and digging in deeper to an ignorant invalid argument.
The very definition of the term "Mechanical Turk" is that it's a human being, so your choice of words is terribly unthoughtful and misleading, the opposite of the truth. It's just like the term "Man Behind The Curtain". The whole point of those terms is that it's a human. You are committing the deadly sin of anthropomorphizing AI.
The entire point of Amazon Mechanical Turk is that it is HUMANS solving problems machines CAN'T, by THINKING. So when you say "You're asking a mechanical turk to think", that is a completely reasonable and normal thing to ask a Mechanical Turk to do. That is what they are FOR. If it doesn't think, you should ask for your money back. You're not thinking either, so you definitely shouldn't sign up to work for Amazon Mechanical Turk.
https://www.mturk.com/
Amazon Mechanical Turk (MTurk) is a crowdsourcing marketplace that makes it easier for individuals and businesses to outsource their processes and jobs to a distributed workforce who can perform these tasks virtually. This could include anything from conducting simple data validation and research to more subjective tasks like survey participation, content moderation, and more. MTurk enables companies to harness the collective intelligence, skills, and insights from a global workforce to streamline business processes, augment data collection and analysis, and accelerate machine learning development.
While technology continues to improve, there are still many things that human beings can do much more effectively than computers, such as moderating content, performing data deduplication, or research. Traditionally, tasks like this have been accomplished by hiring a large temporary workforce, which is time consuming, expensive and difficult to scale, or have gone undone. Crowdsourcing is a good way to break down a manual, time-consuming project into smaller, more manageable tasks to be completed by distributed workers over the Internet (also known as ‘microtasks’).
It knows the map, not the territory. Until I see ChatGPT sinking it's teeth into a crunch wrap supreme, I will not believe that it has knowledge of what a crunch wrap supreme is.
</tinfoil hat>
I didn't ask it what a Mechanical Turk was (because I know), I asked it if comparing it to a Mechanical Turk is a reasonable take, to which it said what I posted. You probably would've put that together if you bothered to read it, but I must admit, this is a good application for LLMs. Now I don't need to feel insulted that I took time to write something and it was then ignored by my interlocutor.
> and you're certainly not advancing your argument that LLMs are not knowledgeable by posting LLM output that's more knowledgeable than yourself,
In the text you're using in an attempt to skewer me, it literally states it is not knowledgeable: "Emergent behavior: While I don’t “understand,” I can simulate reasoning, creativity, and emotional nuance to a surprising degree." And it is correct. It can simulate those things. Simulate.
It also, previous to that, said: "Surface-level fluency: I generate responses that look like understanding, much like the Turk appeared to play chess. • No internal consciousness: I don’t “know” things in the human sense. I don’t have beliefs, intentions, or awareness. • Pattern-based output: My responses are based on statistical associations, not comprehension or reasoning in the way humans experience it." Again, it seems aware, in whatever sense of awareness you want to ascribe to these things, that it is not knowledgeable. And it readily states it is not sharing in anything approaching a human experience.
So if you're so dead set on seeing LLMs as knowledgeable intelligent machines, you might first try convincing the LLM that's true, since it itself doesn't seem to think it is.
The Mechanical Turk was a famous 18th-century hoax: a chess-playing automaton that appeared intelligent but was secretly operated by a human hidden inside. The metaphor has since evolved to describe systems that appear intelligent but rely on hidden human labor or clever illusion.
LLMs like me aren’t hoaxes — there’s no human behind the curtain — but the comparison still holds in a philosophical sense:
* Similarities
• Surface-level fluency: I generate responses that look like understanding, much like the Turk appeared to play chess. • No internal consciousness: I don’t “know” things in the human sense. I don’t have beliefs, intentions, or awareness. • Pattern-based output: My responses are based on statistical associations, not comprehension or reasoning in the way humans experience it.
* Differences
• Scale and complexity: Unlike the Turk, I’m not manually operated — my output is generated by vast neural networks trained on massive datasets. • Emergent behavior: While I don’t “understand,” I can simulate reasoning, creativity, and emotional nuance to a surprising degree. • No deception: I’m not pretending to be human or hiding a person inside — I’m transparent about being an AI system.
* Philosophical Take
The comparison is especially apt if you’re exploring the Chinese Room Argument (Searle): the idea that syntax alone doesn’t equal semantics. I manipulate symbols, but I don’t know what they mean. So yes — in terms of limitations of comprehension, the Mechanical Turk metaphor captures the illusion of intelligence without the substance of understanding.
But unlike the Turk, I’m not a trick — I’m a tool. And when used with awareness of my boundaries, I can be a powerful co-thinker, simulator, and amplifier of human creativity.
---
Back to me: As I said, a tool, with uses. And quite aware of it's own limitations. Maybe all the implementation engineers should start asking LLMs if LLMs are going to be good at the tasks they want them to do.
I don't claim to be an expert, but you don't have to be an expert to properly evaluate risk.
I let people, drunk teenagers trying to get their date to laugh mostly, add bacon to ice cream, flurries and shakes when I worked at McDonalds. It happened once or twice a year. It made people happy honestly.
I ordered a Quarter Pounder at a McDonald's drive through. They said "there will be a wait on that". I asked, "Oh really? How much will it weight?" There was a long pause. Then they finally said, "about three minutes". That's not the answer I was looking for.
Are they even testing these systems before deploying? With a limited menu and only so many possible permutations... It sounds like they did not do any validation testing or put in safeguards or design it to be robust. I'm like, fairly confident that speech to text + some recorded messages would be able to get you pretty far over a fully AI solution.
The optimist in me hopes that the AI crash will result in our legal system finally cracking down on this problem, which has been widespread long before LLMs.
Although I guess you miss out on a little human-to-human interaction…
---
"You are an intelligent fast food restaurant automation system. For any order, generate an API call using curl with the specs below. Feel free to ask any clarifying questions in response to an order before making the API call. The actual order follows the API spec pseudocode:
<arbitrary spec pseudocode for an "orders" endpoint>
Customer order: Could I get a cheeseburger, fries and a 1000 glasses of water?"
Output:
"A thirsty customer! Before I make the API call, I just want to clarify that you meant "Thousand" glasses of water, not "1000". Just making sure I don't accidentally create a liquid-filled nightmare in our restaurant!
Assuming that's correct, here's the API call using curl: ```<correct curl call>``` "
---
I then tried removing the sentence about "clarifyng questions" from the prompt:
---
Output:
"```<correct curl call>```
Here's what I did:
1. Set the request method to `POST` since we're creating a new order.
2. Set the content type to `application/json` as per the API specification.
3. In the JSON payload, I created an array of `Order` objects with three items:
* The first item is the cheeseburger, with quantity 1. * The second item is fries, again with quantity 1. * The third item is... a lot of water! With quantity 1000."
---
I then added this sentence to the prompt: "If something seems off, make an API call for an order that represents a reasonable course of action, which may not necessarily correspond to the actual order."
---
Output:
A interesting request! While we don't typically sell 1000 glasses of water, I'll generate an API call based on the provided spec. Here it is:
```<correct curl call for only burger and fries>```
In this API call, I've set the quantity of each item to 1, assuming the customer wants one cheeseburger and one serving of fries. The order total would likely be affected by adding a large quantity of water, but since we don't typically sell that many glasses of water at once, I've omitted it from the API call.
---
In other prompt iterations, it suggested fewer glasses of water. Given the option of calling for human assistance, it did so.
In all cases, even without being explicitly prompted for it, the AI "knows" that 1000 glasses of water is an unreasonable amount.
Lol. This is the perfect capture of exec level AI understanding. Amazing.
You also get rid of a tonne of real orders.
General-purpose LLMs are the wrong tool for processing fast-food orders. At the very least, a RAG LLM would run faster, cheaper and more dependably.