This is the reasoning deficit. Models are very good at generating large quantities of truthy outputs, but are still too stupid to know when they've made a serious mistake. Or, when they are informed about a mistake they sometimes don't "get it" and keep saying "you're absolutely right!" while doing nothing to fix the problem.
It's a matter of degree, not a qualitative difference. Humans have the exact same flaws, but amateur humans grow into expert humans with low error rates (or lose their job and go to work in KFC), whereas LLMs are yet to produce a true expert in anything because their error rates are unacceptably high.
> It should load quicker compared to traditional React apps where the browser loads the HTML, then loads the JS bundle, and only then renders a loading skeleton while likely triggering more requests for data.
Then your JS bundle is broken.
Promises exist. Modules exist. HTTP/2+ exists. You can load data while you are loading a small amount of JS required to render that data while you are loading other parts of your JS.
If everything is sequential: load giant JS bundle -> fetch -> render, that's because someone architected it like that. Browsers give you all the tools you need to load in parallel, if you don't use them then it's not the browser's fault.
You do not need SSR or rehydration. That's just Vercel propaganda. They saw that people are doing a stupid thing and decided to push a complex solution to it. Why? It makes them money.
You cannot load any data in a regular React application before you loaded both React and your React components that trigger the fetch.
If you use code splitting, your initial bundle size can be smaller, yes. That's about it.
I guess in theory you can hack together static loading skeletons that you then remove when React loaded your initial bundle, but that's certainly far from a common approach. By that standard, the vast majority of JS bundles would be "broken".
> You cannot load any data in a regular React application before you loaded both React and your React components that trigger the fetch.
You totally can!
Don't call fetch directly from a component - it's brittle. Write a hook to abstract that into one place. In your hook you can support prefetching by awaiting the promise you fired before you loaded your JS bundle (if you don't want to modify the server), or else take advantage of the browser cache. In this way your data and code can load in parallel.
Is it common? Not really. But it's a technique that is in the toolbox of a conscientious webdev.
So you’re skipping any sort of a build pipeline? You’re not going to bundle, so no code minification? You’re going to skip tests? And everyone who uses these things just does them to “feel grown up” and not for any particular benefit or purpose beyond that?
You can use esbuild to build your entire project with a single command. Node has a built in test runner. You only need the complexity because you're convinced you need it.
No. My point is more nuanced than that. All of the things in the article have value to someone, but their value to you is defined in terms of how much better they make your product.
If you spend so much time on the cumulation of product-adjacent activities that you don't make a good product, then their cumulative value to you was negative.
But I do, personally, love a good build system. The value is extremely high and it only takes 10 minutes to set one up.
Not so sure these days tbh.
People are trying to shove as much shiny tools as possible instead of sometimes writing 10 vanilla JS lines and proceed to next feature or project.
Maybe it’s already exhausted, but left-pad, is-odd, is-even are still my examples for people.
Sucks for everyone else is what I'm saying. 100% of people should be allowed access, not be preempted from it in order to protect the value of exalted tech cartels.
No, that is completely wrong. It is exactly because the questions are not identical that the system works. That is what allows for multiple versions of a popular, important question to catch attention from search engines, and send everyone to the same, correct place.
Perhaps your objection is that, because the target question is not literally identical (for example, maybe a code sample has different variable names, or the setup has an irrelevant difference in the container type used for a collection, etc.) that the answers don't literally answer the new version of the question. That is completely missing the point. It's not a forum. The Q&A format is just the way that information is being presented. Fixing the issue in your, personal code is not, and never has been, the goal.
You are positing that only questions with cosmetic or extraneous differences are marked as duplicates.
That's not the case. As a maintainer of a popular project who has engaged with thousands of Qs on SO related to that project, I've seen many Qs marked as duplicate where the actual answer would be different in a non-trivial manner. When I look at who all moderated on those Qs, they are usually users who haven't contributed to that topic at SO.
Yes, it is. I have been active on both the main and meta sites for many years. I have seen so many of these complaints and they overwhelmingly boil down to that. And I have gotten so unbelievably stressed out on so many occasions trying to explain to people why their trivial objections are missing the point of the site completely.
> I've seen many Qs marked as duplicate where the actual answer would be different in a non-trivial manner.
Please feel free to cite specific examples. I'll be happy to explain policy.
> When I look at who all moderated on those Qs, they are usually users who haven't contributed to that topic at SO.
Have you considered that the problem here is not insufficient explanation of policy?
There's this thing that some programmers do a lot, where it's the users who are wrong. Using it wrong, approaching it wrong, thinking about it wrong, wanting the wrong thing. Just not understanding enough the masterwork that the programmers created.
What this view misses is that the users are the point. If one user gets it wrong, sure, maybe it's the user. But broadly the point of software is to serve and adapt to users, and developers who forget that are starting an argument that they cannot win in the long term.
It's especially wild to see you talking like this on an article about how Stack Overflow is just about dead. It needed changes a decade ago, but everyone just hunkered down and defended the existing approach. The policies you are somehow still defending are a big part of what doomed the site.
The site was a consensus of what Jeff and Joel and their associated blogging communities who started posting on Stack Overflow wanted. There was some tension between those two communities about what should be there, but that's where it started.
In the early days, onboarding was done fairly actively with a reasonable amount of the community participating in answering and community moderation - shaping it.
That portion of the community - both answering and moderating was key for onboarding.
However, as Stack Overflow got popular, a smaller and smaller percent of the community was actively answering and participating in community moderation - and onboarding of new people became more and more difficult.
Here I lay the responsibility nearly completely at the feet of corporate. The friction for moderation was increased at the same time that it became popular and thus harder for the community to moderate.
Making it easier moderate and help people understand the site meant that either you needed a larger part of the now very large number of people participating on the site or the ease of community moderation needed to be dialed back.
This is also where rudeness became more and more common. There are two parts to this - first rudeness takes no points to get to that level of moderation. It doesn't have any limited pool of votes that you deplete. Secondly, not everything was rude. With the smaller and smaller pool of community moderation people were shorter in their attempts to onboard a person. You couldn't write a paragraph in a comment and spend 10 minutes on one person when spending 1 minute on 10 different people was more likely to help someone. The shortness of responses was interpreted by the person asking was being perceived as rude.
Lastly, StackOverflow was designed as a Q&A site and attempted to minimize some of the things that were seen as failings described in A Group Is Its Own Worst Enemy ( https://news.ycombinator.com/item?id=23723205 ) - Clay Shirky was a mentor of Jeff and was on the original Stack Overflow board. It tried (and for a long time succeeded at) handling scale... though when Stack Overflow's ability to handle scale failed, it was the moderation tools and the ability for the people participating in community moderation to help surface the good questions to be answered and have the questions that needed work to be properly answerable in the Q&A format that Stack Overflow was designed around (not in a forum format) that suffered.
What you're missing is that random people who come to Stack Overflow to ask a question (of a sort that doesn't meet the site's standards) are not my "users". I don't care in the slightest about these metrics of "dead-ness", and showing them to me another hundred times will not change my mind about that.
Because from my perspective, it has never been about how many questions are asked per day, or how many ad impressions the site owners get. (I don't see a dime from it, after all.) From my perspective, way too many questions got asked. It is more than three times as many publicly visible and still-open questions, as there are articles on Wikipedia. For a scope of "practical matters about writing code", as compared to "any real-world phenomenon important enough for reliable sources to have written about it".
I am not trying to win the argument about what people want. I am only establishing that the goal is legitimate, and that people who share that goal should be permitted to congregate in public and try to accomplish something. I do not share your goals. The community is not like software, and "serving and adapting to users" does not benefit the people doing the work. We never arranged to have the kind of "users" you describe.
As a former Wikipedia administrator, I think one of the things that Wikipedia has done exactly right is to strongly prioritize readers first, editors second, and administrators third. The unofficial Wikipedia administrator symbol is a mop, because it's much more a position of responsibility than it is a position of power.
I obviously think you and other user-hostile people should be permitted to congregate and accomplish something. What I object to in Stack Overflow's case is the site being taken over by people like that, serving themselves and their own preferences with such vigor that they alienated vast numbers of potential contributors, putting the site on a path of decline from which is unlikely to recover.
Even by your own terms, having a place for some (conveniently unspecified) group to "congregate in public and try to accomplish something" looks certain to be a failure. However much you don't care about deadness or declining revenue, the people paying the bills surely do. Stack Overflow was only a success because it served and adapted to users.
But I give you points for being honest about your hostility to the entire point of the site. It not only makes it clear why it's failing, but it'll keep people from being sorry when it gets closed down.
Deadness is the symptom, not the cause. Users don't avoid SO because it's dead, but rather, SO is dead because users avoid it. It's up to you to figure out why users are avoiding it. Hint: They've been telling you quite loudly.
There's another thread on the front page about IPv6 where someone had a good analogy: IPv4 vs IPv6 is like Python 2 vs 3. The Python 2 diehards continued arguing furiously to an emptier and emptier room. They never felt they were proven wrong, and the intensity of the argument never diminished but the argument was with fewer and fewer people until they were just arguing with themselves as the world moved on without them.
And that's exactly what happened to Stack Overflow, and you're one of those guys still trying to promote the use of Python 2.7 in 2026, after the horse is long gone. Everyone has left, the lights are off in the empty debate hall and you're standing there at the podium telling a bunch of chairs and desks why everyone actually agrees with you. You might want to reflect on why you hold such fervent beliefs that are in direct contradiction with observable reality. Can I guess you had a lot of reputation points and you desperately don't want to believe they're worthless now?
> It's up to you to figure out why users are avoiding it. Hint: They've been telling you quite loudly.
No, it is not up to me to figure that out. I have heard it said quite loudly many times, over a period of many years.
What you are missing is: I. Do. Not. Care.
The goal was never for the site to be "not dead". The goal was for the site to host useful information that is readily found.
The site already has tons of useful information. But it's drowning in... much less useful information, and Google has become much worse (to some extent intentionally) at surfacing the good parts.
> And that's exactly what happened to Stack Overflow, and you're one of those guys still trying to promote the use of Python 2.7 in 2026
This is a bizarre thing to say to me, of all people. I am always the one catching flak for telling people that 2.7 had to go, that the backwards-incompatible changes were vital, that the break wasn't radical enough, and that people were given way more time to switch over than they should have needed.
But really, the feedback for Stack Overflow is trying to take it in the direction of places that existed long beforehand. If you want forums, you know where to find them. And now you can also find LLMs. Which, as commonly used by people seeking programming help, are basically a grizzled forum guy in a can.
>Everyone has left, the lights are off in the empty debate hall and you're standing there at the podium telling a bunch of chairs and desks why everyone actually agrees with you.
"Everyone actually agrees with [me]" is the polar opposite of what I actually believe and am actually saying. I am well aware that the model is unpopular. My point is that the popularity of the model is irrelevant to me.
> Can I guess you had a lot of reputation points and you desperately don't want to believe they're worthless now?
I have a lot of reputation points (the site still exists), far more than I ever felt I deserved, and I never really felt like they were worth anything. A huge percentage of them come from an answer to a terrible question (that was still terrible after heroic attempts at editing; this all happened long before there was a common understanding of the purpose of question closure or what would make good standards for questions) that, once I understood things properly, I closed and tried to get deleted. Over the last few years, with that new understanding, I have been trying to give away my superfluous reputation points in bounties, trying to get missing answers written for the few really good questions lacking good answers that I identify, always to no avail (the bounty system promptly became a honeypot for ChatGPT hallucinations as soon as ChatGPT became available).
You do not know me or my motivations in the slightest.
> The goal was never for the site to be "not dead"
ok? fine then. If you think it's fine for the site to be dead then please stop spamming comments defending it. It doesn't need any defence to stay dead and such defence is not useful.
Response to child comment: no, you are not replying to people telling you why you need to care about a thing. You are mostly replying randomly throughout the thread and telling people why they are wrong.
I am only responding to many people trying to explain why I should care about the thing I don't care about. The defense is useful because a) it being "dead" by these metrics is unimportant; b) people are blaming a community for mistreating them, when they came in without any intent of understanding or adapting to that community; c) other sites in this mold exist, and are trying to establish themselves.
You appear to have linked the canonical, which has a few duplicates marked. All are asking about isolating one channel, as far as I can tell. This canonical is literally titled "ffmpeg: isolate one audio channel". One of them also asks about "downmixing" to mono after isolating the channel (which I guess means marking the audio format as mono so that that isolated channel will play on both speakers), but that is trivial. And you see the same basic techniques offered in the answers: to use `-map-channel` or the `pan` audio filter. The other one explicitly wants a panned result, i.e. still stereo but only on one side; the logic for this is clear from the explanation in the canonical answer.
The point is to show the technique, not to meet individual exact needs. Stack Overflow doesn't need separate "how do I get the second line of a file?" and "how do I get the third line of a file?" questions.
The orig wants a mono output with one of the original channels as signal source. This involves downmixing i.e. rematrixing the audio.
The dupe want to just mute one of the channels, not repan it. One can't apply map_channel to do what the dupe wants.
One can use a couple of methods to achieve the dupe, including pan. But the syntax of pan needed for the dupe case is not the same as the orig, or deducible from it. They need to consult the docs (fortuitously, the dupe case is an illustrated example) or get a direct answer. The 'technique' shown in the orig is not intuitively adaptable to the dupe - one needs to know about the implicit muting that pan applies, which is not documented or evident in the orig answer. So it's not a duplicate of the source Q.
> it looks to me like I could figure it out pretty easily from what's written there
Really? Wanna give it a try then, without looking up any other documentation? I've used ffmpeg plenty of times, but it doesn't seem obvious to me how I'd mute one audio channel.
From your other comments it sounds like you believe SO should have less content. Why? How would SO be improved by forcing people to figure something like this out from the existing answer? I just don't understand the benefit to having that question marked as a duplicate and deleted.
I've long wondered the same thing about wikipedia. Why does wikipedia delete well written pages about obscure topics? Is their hard disk full? Does every page cost them money? Does google search struggle at scale? I don't understand the benefit to deleting good content.
> Really? Wanna give it a try then, without looking up any other documentation?
I mean, that's not the point of SO or any of the SE sites. It's not there so you don't have to do some more work to get to an answer.
From that answer, if you're still having issues, you form a question around:
"I found this answer on [SO](link), which lead me in this direction and found these [documents](link), however I am still having issues with getting the thing to work correctly when i run this bit of code, ```code```, from the output it says it's doing this or that, but when i check something, i find that it's not doing what it claims in the outputs. What might I have missed?"
And even then, that's still a fairly shaky question.
Most people don't know how to write questions, which is most of what this whole comment section is complaining about.
> that's not the point of SO or any of the SE sites. It's not there so you don't have to do some more work to get to an answer.
My brain is spitting out a parse error on this sentence. Too many double negatives.
Zahlman was claiming above that the "duplicate" question linked earlier in the thread wasn't a useful question. Its not useful because if you read the accepted answer in the original thread, you can figure it out easily.
Prove it then. Figure it out easily for us.
I think the point of SO is for people to look up the answers to questions they have. If people have similar but distinct questions with different answers, it seems objectively better to surface both SO threads. Ideally they'd be linked together so if I accidentally stumble on the wrong question, there's a link to the question I'm actually interested in.
> "I found this answer on [SO](link)
Why bother with all of that? I mean, it sounds like all those extra words are all to grovel sufficiently to the SO moderator-gods, hoping in their capricious anger they won't mark your question as a duplicate and wipe it from the internet. Grovelling doesn't help the question asker or the question answerer.
As a user, my problem with SO isn't that people ask bad questions. Its usually that the question I actually have - if its been asked - has long ago been deleted as a duplicate. And the only question remaining on the site is subtly different from the problem I'm actually facing. Or the answer is tragically out of date. Perhaps if people asked better questions, the moderators would be happier. But the site shouldn't be run purely for the benefit of its moderators.
It became a meme. "How do I do X in javascript?" "Here's how you do it using jQuery." "But I'm not using jquery." "Question closed!"
> Zahlman was claiming above that the "duplicate" question linked earlier in the thread wasn't a useful question. Its not useful because if you read the accepted answer in the original thread, you can figure it out easily.
No, I was not. Duplicate questions are often very useful.
They just... shouldn't host separate answers in a separate place, because that leads to a) duplicated answering effort and b) dilution of results for third parties who search for the information later.
Having a question like this linked as a duplicate highlights the fact that the same fundamental problem can be conceived of in different ways, and appear different due to ancillary requirements.
> If people have similar but distinct questions with different answers, it seems objectively better to surface both SO threads. Ideally they'd be linked together
But we aren't talking about different answers. A bit of adaption to ancillary details is expected. Otherwise there would be no duplicate questions, and also no reason to ever try to have Stack Overflow in the first place, because asking on a forum would be fine. Searching the Internet to figure out how to fix your code could never work and never help, because obviously nobody else has ever written your code before.
But problem-solving doesn't actually work that way.
Closing duplicate questions as duplicates is linking them together.
> Why bother with all of that? I mean, it sounds like all those extra words are all to grovel sufficiently to the SO moderator-gods
This is because you are still approaching the site with the mindset of "what do I have to do to get these other people to give me the information I want?"
But it's not (just) about you. A good question will be seen by many other people.
> Its usually that the question I actually have - if its been asked - has long ago been deleted as a duplicate.
Duplicates are not automatically deleted and not ordinarily manually deleted.
> And the only question remaining on the site is subtly different from the problem I'm actually facing.
Would reading the answers give you the information need to solve the problem, after first putting in the expected effort to isolate a single problem? If not, why not? That's what we care about.
> Or the answer is tragically out of date.
My experience has been that old answers are not actually "out of date" nearly as often as people would expect. But when they are, this is fixed by putting a new answer on the existing question. The bounty system was created largely for this reason. It has proven a failure, for a variety of reasons, but that's a failure of understanding gamification, not a problem with the model.
> Perhaps if people asked better questions, the moderators would be happier. But the site shouldn't be run purely for the benefit of its moderators.
It's frankly infuriating to read things like this. I have already said so many times that the overwhelming majority of the people objected to are not moderators, but people insist on using that language, not making any effort to understand the existing community, and then wondering why they feel unwelcome. More importantly, though, we are going out of our way to try to build something that benefits everyone. While most people asking questions are thinking only of themselves.
from the perspective of people who aren't explicitly trying to teach on their own initiative, overall the site has outlived its purpose. In that time it drew way too many total questions to surface what's actually valuable; between that and no functional search (the internal search was always bad; Google et. al. got worse over time, partly intentionally) you're lucky to find anything valuable.
I'm not generally worried about out-of-date answers; the truly outdated answers are mostly on outdated questions, describing situations that don't come up any more or premises that are no longer valid for ordinary programmers (e.g., fixing problems with obsolete tools).
Combing through to curate properly is too little, too late now. Much stronger (but polite, of course) gatekeeping was required earlier on, which in turn required (among other things) proper means for communication between "core" users and the public. At this point, it's best to start over (hence the part where I'm now a moderator at Codidact).
There's a lot more I want to say, but I don't have it organized in my head and this is way downthread already. Perhaps I could interest you in a hypothetical future blog post?
I do not remember any specific examples, but when I still used SO, I've come across many cases personally where a question closely matching a problem I had was closed as a duplicate of another question that asked about a related, but different problem and had an answer that was not appropriate for my problem and the supposedly duplicate question.
This significantly decreased the utility of clicking on SO links for me, to the point where I would avoid going to search results from SO first.
The comments here are teeming with others voicing similar experiences.
It is quite... something to read your response to this, which pretty much comes across as "nu-uh!", garnished with an appeal to "policy".
I think your SO-specific bubble is a little different from most other people's. I've no doubt that overwhelmingly, the dupes are dupes, but on the other hand, the false positives you're discounting are overwhelming the user experience.
> many cases personally where a question closely matching a problem I had was closed as a duplicate of another question that asked about a related, but different problem and had an answer that was not appropriate for my problem and the supposedly duplicate question.
Yes.
We consider that duplicate.
Because the point is whether the question is duplicate, not whether the problem is duplicate. The point is not to solve the problem, so it isn't interesting whether the question is "appropriate to" the problem. The point is to give you the information you need.
I don't understand how you can read all this and conclude that people get the information they need.
In fact, your latest response is so far out that I've started to seriously wonder if you're trying to troll. If you aren't: sorry, just trying to tell you how this comes across as absurdly disconnected. If you are: you're bad at trolling, or a master at satire. Either way, I'm outta here.
How does "give you the information you need" mesh with "The point is not to solve the problem"? They seem like mutually exclusive goals for 95% of cases.
^ this whole chain-of-interaction is a wonderful reminder of why I left SO: It was like seeing a movie trailer about a remake of some nearly forgotten B- horror film one was unfortunately allowed to watch when far too young.
Spoiler warning for those who havent seen this movie before:
Callous disregard for the utility and purpose of both the 'Q' and 'A' users; thinly veiled in a 'you don't get to tell me what i care about', wrapped in a 'my concept of how to moderate is just the way it is; if you don't like it, go F* yourself' package, trimmed with a ribbon of 'who do these Lusers that pay the bills think they are' directed at both the site owners (who write the checks to pay the bills) and all three relevant types of visitors, Q's, A's and those who neither ask, nor answer questions, but do see Advertisements and indirectly generate the income which the site owners use to write checks. But who cares?!, since Mods are not being paid (or paid well enough) to adjust a maladjusted concept of 'the way things are' into 'giving a shit' for anyone. Closed with some more vitriol declaring the site still exists and continues to be useful (as nipples on a chicken).
WASH, RINSE, REPEAT...
That was so last decade; I just stopped giving a damn, removed my browser bookmarks and learned to skim past less frequent and less relevant links to useless and meaningless SO pages when they appear in search results.
The funniest outcome is that LLMs will continue to ingest the diminishingly accurate content of sites like this and continue to degrade the utility of even the most broadly defensible LLM use case scenario.
phew, haven't thought that deeply about SO in at least 4 ... wait its 2026, make that 5 years. Good riddance to the the Whole Lot of you.
Exactly... I'm getting a laugh out of this thread because it's so easy to spot the power-trippers who are enraged at how their fiefdom is rapidly going extinct.
The reason that interior doors in general open inwards is fire safety. Doors that only open outwards can be obstructed from the outside, preventing evacuation.
> people are very annoyed with Apple pushing for signing off the resulting product.
Apple is very much welcome to push for signing off of software that appears on their own store. That is nothing new.
What people are annoyed about is Apple insisting that you can only use their store, a restriction that has nothing to do with safety or quality and everything to do with the stupendous amounts of money they make from it.
It's literally the case of Apple requiring signing the binary to run on the platforms they provide, Apple doesn't have say on other platforms. It is a very similar situation with local governments.
Also, people complain all the time about rules and regulations for making stuff. Especially in EU, you can't just create products however you like and let people decide if it is safe to use, you are required to make your products to meet certain criteria and avoid use certain chemicals and methods, you are required to certify certain things and you can't be anonymous. If you are making and selling cupcakes for example and if something goes wrong you will be held responsible. Not only when things go wrong, often local governments will do inspections before letting you start making the cupcakes and every now and then they can check you out.
Software appears to be headed to that direction. Of course du to the nature of software probably wouldn't be exactly like that but IMHO it is very likely that at least having someone responsible for the things a software does will become the norm.
Maybe in the future if your software leaks sensitive information for example, you may end up being investigated and fined if not following best practices that can be determined by some institute etc.
That's not a very compelling counterexample, when you consider how often countries with governments force other countries with government to do as they want, often with nothing but economic or soft power.
> Apple is very much welcome to push for signing off of software that appears on their own store.
Just to be clear, apps have to be notarized/signed to run on an Apple device. For macOS, notorized apps aren't required to be distributed in the App Store. Due to sandbox restrictions, some dev tools are distributed independently.
Or there are two versions: a less capable version for the App Store and a more capable version distributed independently.
Just the other day ChatGPT implemented something that would have taken me a week of research to figure out: in 10 minutes. What do you call that speedup? It's a lot more than 10x.
On other days I barely touch AI because I can write easy code faster than I can write prompts for easy code, though the autocomplete definitely helps me type faster.
The "10x" is just a placeholder for averaging over a series of stochastic exponents. It's a way of saying "somewhere between 1 and infinity"
> Just the other day ChatGPT implemented something that would have taken me a week of research to figure out: in 10 minutes. What do you call that speedup? It's a lot more than 10x.
Can you share what exactly this was? Perhaps I don't do anything exciting or challenging, but personally this hasn't happened to me so I find it hard to imagine what this could be.
Instead of AI companies talking about their products, I think the thing to really sell it for me would be an 8 hour long video of an extremely proficient programmer using AI to build something that would have taken them a very long time if they were unassisted.
Sure. I needed to draw some parametric and smooth Bézier curves. LLMs are beasts at figuring out the appropriate equations. It would have taken me forever to work out where all the control points should go.
It's a matter of degree, not a qualitative difference. Humans have the exact same flaws, but amateur humans grow into expert humans with low error rates (or lose their job and go to work in KFC), whereas LLMs are yet to produce a true expert in anything because their error rates are unacceptably high.
reply