You must log in or register to comment.
A big issue that a lot of these tech companies seem to have is that they don’t understand what people want; they come up with an idea and then shove it into everything. There are services that I have actively stopped using because they started cramming AI into things; for example I stopped dual-booting with Windows and became Linux-only.
AI is legitimately interesting technology which definitely has specialized use-cases, e.g. sorting large amounts of data, or optimizing strategies within highly restrained circumstances (like chess or go). However, 99% of what people are pushing with AI these days as a member of the general public just seems like garbage; bad art and bad translations and incorrect answers to questions.
I do not understand all the hype around AI. I can understand the danger; people who don’t see that it’s bad are using it in place of people who know how to do things. But in my teaching for example I’ve never had any issues with students cheating using ChatGPT; I semi-regularly run the problems I assign through ChatGPT and it gets enough of them wrong that I can’t imagine any student would be inclined to use ChatGPT to cheat multiple times after their grade the first time comes in. (In this sense, it’s actually impressive technology - we’ve had computers that can do advanced math highly accurately for a while, but we’ve finally developed one that’s worse at math than the average undergrad in a gen-ed class!)
The answer is that it’s all about “growth”. The fetishization of shareholders has reached its logical conclusion, and now the only value companies have is in growth. Not profit, not stability, not a reliable customer base or a product people will want. The only thing that matters is if you can make your share price increase faster than the interest on a bond (which is pretty high right now).
To make share price go up like that, you have to do one of two things; show that you’re bringing in new customers, or show that you can make your existing customers pay more.
For the big tech companies, there are no new customers left. The whole planet is online. Everyone who wants to use their services is using their services. So they have to find new things to sell instead.
And that’s what “AI” looked like it was going to be. LLMs burst onto the scene promising to replace entire industries, entire workforces. Huge new opportunities for growth. Lacking anything else, big tech went in HARD on this, throwing untold billions at partnerships, acquisitions, and infrastructure.
And now they have to show investors that it was worth it. Which means they have to produce metrics that show people are paying for, or might pay for, AI flavoured products. That’s why they’re shoving it into everything they can. If they put AI in notepad then they can claim that every time you open notepad you’re “engaging” with one of their AI products. If they put Recall on your PC, every Windows user becomes an AI user. Google can now claim that every search is an AI interaction because of the bad summary that no one reads. The point is to show “engagement”, “interest”, which they can then use to promise that down the line huge piles of money will fall out of this pinata.
The hype is all artificial. They need to hype these products so that people will pay attention to them, because they need to keep pretending that their massive investments got them in on the ground floor of a trillion dollar industry, and weren’t just them setting huge piles of money on fire.
I know I’m an enthusiast, but can I just say I’m excited about NotebookLLM? I think it will be great for documenting application development. Having a shared notebook that knows the environment and configuration and architecture and standards for an application and can answer specific questions about it could be really useful.
“AI Notepad” is really underselling it. I’m trying to load up massive Markdown documents to feed into NotebookLLM to try it out. I don’t know if it’ll work as well as I’m hoping because it takes time to put together enough information to be worthwhile in a format the AI can easily digest. But I’m hopeful.
That’s not to take away from your point: the average person probably has little use for this, and wouldn’t want to put in the effort to make it worthwhile. But spending way too much time obsessing about nerd things is my calling.
From a nerdy perspective, LLMs are actually very cool. The problem is that they’re grotesquely inefficient. That means that, practically speaking, whatever cool use you come up with for them has to work in one of two ways; either a user runs it themselves, typically very slowly or on a pretty powerful computer, or it runs as a cloud service, in which case that cloud service has to figure out how to be profitable.
Right now we’re not being exposed to the true cost of these models. Everyone is in the “give it out cheap / free to get people hooked” stage. Once the bill comes due, very few of these projects will be cool enough to justify their costs.
Like, would you pay $50/month for NotebookLM? However good it is, I’m guessing it’s probably not that good. Maybe it is. Maybe that’s a reasonable price to you. It’s probably not a reasonable price to enough people to sustain serious development on it.
That’s the problem. LLMs are cool, but mostly in a “Hey this is kind of neat” way. They do things that are useful, but not essential, but they do so at an operating cost that only works for things that are essential. You can’t run them on fun money, but you can’t make a convincing case for selling them at serious money.
Totally agree. It comes down to how often is this thing efficient for me if I pay the true cost. At work, yes it would save over $50/mo if it works well. At home it would be difficult to justify that cost, but I’d also use it less so the cost could be lower. I currently pay $50/mo between ChatGPT and NovelAI (and the latter doen’t operate at a loss) so it’s worth a bit to me just to nerd out over it. It certainly doesn’t save me money except in the sense that it’s time and money I don’t spend on some other endeavor.
My old video card is painfully slow for local LLM, but I dream of spending for a big card that runs closer to cloud speeds even if the quality is lower, for easier tasks.
but I dream of spending for a big card that runs closer to cloud speeds
Nvidia’s new motto: “An A100 at every home”
I’ll pay a bit more for the next model of my phone that promises on device ai, or actually already did. We’ll see if that turns into something useful.
So far the bits and pieces I’ve played with are not generative ai, but natural language processing and inferencing. The improved features definitely make my phone a more useful piece of hardware, but not revolutionary
Being able to summarize and answer questions about a specific corpus of text was a use case I was excited for even knowing that LLMs can’t really answer general questions or logically reason.
But if Google search summaries are any indication they can’t even do that. And I’m not just talking about the screenshots people post, this is my own experience with it.
Maybe if you could run the LLM in an entirely different way such that you could enter a question and then it tells you which part of the source text statistically correlates the most with the words you typed; instead of trying to generate new text. That way in a worse case scenario it just points you to a part of the source text that’s irrelevant instead of giving you answers that are subtly wrong or misleading.
Even then I’m not sure the huge computational requirements make it worth it over ctrl-f or a slightly more sophisticated search algorithm.
Multiple times now, I’ve seen people post AI summaries of articles on Lemmy which miss out really, really important points.
Well an example of something I think it could solve would be: “I’m trying to set this application up to run locally. I’m getting this error message. Here’s my configuration files. What is not set up correctly, or if that’s not clear, what steps can I take to provide more helpful information?”
ChatGPT is always okay at that as long as you have everything set up according to the most common scenarios, but it tells you a lot of things that don’t apply or are wrong in the specific case. I would like to get answers that are informed by our specific setup instructions, security policies, design standards, etc. I don’t want to have to repeat “this is a Java spring boot application running on GCP integrating with redis on docker… blah blah blah”.
I can’t say whether it’s worth it yet, but I’m hopeful. I might do the same with ChatGPT and custom GPTs, but since I use my personal account for that, it’s on very shaky ground to upload company files to something like that, and I couldn’t share with the team anyway. It’s great to ask questions that don’t require specific knowledge, but I think I’d be violating company policy to upload anything.
We are encouraged to use NotebookLLM, however.
Even the success case is a failure. I’ve had several instances where Google returned a nice step by step how to answer a user’s questions, correctly, but I can’t forward the link and trust they’ll see the same thing
you could enter a question and then it tells you which part of the source text statistically correlates the most with the words you typed; instead of trying to generate new text. That way in a worse case scenario it just points you to a part of the source text that’s irrelevant instead of giving you answers that are subtly wrong or misleading.
Isn’t this what the best search engines were doing before the AI summaries?
The main problem now is the proliferation of AI “sources” that are really just keyword stuffed junk websites that take over the first page of search results. And that’s apparently a difficult or unprofitable problem for the search algorithms to solve.
That’s what Google was trying to do, yeah, but IMO they weren’t doing a very good job of it (really old Google search was good if you knew how to structure your queries, but then they tried to make it so you could ask plain English questions instead of having to think about what keywords you were using and that ruined it IMO). And you also weren’t able to run it against your own documents.
LLMs on the other hand are so good at statistical correlation that they’re able to pass the Turing test. They know what words mean in context (in as much they “know” anything) instead of just matching keywords and a short list of synonyms. So there’s reason to believe that if you were able to see which parts of the source text the LLM considered to be the most similar to a query that could be pretty good.
There is also the possibility of running one locally to search your own notes and documents. But like I said I’m not sure I want to max out my GPU to do a document search.
You’re using the wrong tool.
Hell, notepad is the wrong tool for every use case, it exists in case you’ve broken things so thoroughly on windows that you need to edit a file to fix it. It’s the text editor of last resort, a dumb simple file editor always there when you need it.
Adding any feature (except possibly a hex editor) makes it worse at its only job.
… I don’t use Notepad. For anything. Hell, I don’t even use Windows.
Not sure where the wires got crossed here.
Yes as others said, the op mentioned notepad and you said notebookllm.
I thought you were talking about notepad and it’s new ai features.
I had no idea notepad + AI was a thing. It sounds farcical, so I assumed wrongly it was a reference to NotebookLLM. My mistake. I shouldn’t have assumed OP was just being dismissive.
Then either you replied with your first post to the wrong post or you misread “windows putting AI into notepad” as notebookLLM? Because if not there is nothing obvious connecting your post to the parent
I don’t think anyone is putting AI into Notepad. It reads to me like a response to NotebookLLM but maybe I was wrong.
I did at least explain what my vision is and why I wanted it which… doesn’t sound anything like Notepad, I think.
I don’t think […]
Well, you think wrong: https://blogs.windows.com/windows-insider/2024/11/06/new-ai-experiences-for-paint-and-notepad-begin-rolling-out-to-windows-insiders/
I did at least explain what my vision is and why I wanted it which… doesn’t sound anything like Notepad, I think.
Might be, but the person you responded to wrote about windows putting AI into notepad, so everyone assumed you were responding to that and not writing about something that was not even mentioned
The answer is that it’s all about “growth”. The fetishization of shareholders has reached its logical conclusion, and now the only value companies have is in growth. Not profit, not stability, not a reliable customer base or a product people will want. The only thing that matters is if you can make your share price increase faster than the interest on a bond (which is pretty high right now).
As you can see, this can’t go on indefinitely. And also such unpleasantries are well known after every huge technological revolution. Every time eventually resolved, and not in favor of those on the quick buck train.
It’s still not a dead end. The cycle of birth, growth, old age, death, rebirth from the ashes and so on still works. It’s only the competitive, evolutionary, “fast” model has been killed - temporarily.
These corporations will still die unless they make themselves effectively part of the state.
BTW, that’s what happened in Germany described by Marx, so despite my distaste for marxism, some of its core ideas may be locally applicable with the process we observe.
It’s like a worldwide gold rush IMHO, but not even really worldwide. There are plenty of solutions to be developed and sold in developing countries in place of what fits Americans and Europeans and Chinese and so on, but doesn’t fit the rest. Markets are not exhausted for everyone. Just for these corporations because they are unable to evolve.
Lacking anything else, big tech went in HARD on this, throwing untold billions at partnerships, acquisitions, and infrastructure.
If only Sun survived till now, I feel they would have good days. What made them fail then would make them more profitable now. They were planning too far ahead probably, and were too careless with actually keeping the company afloat.
My point is that Sun could, unlike these corporations, function as some kind of “the phone company”, or “the construction company”, etc. Basically what Microsoft pretended to be in the 00s. They were bad with choosing the right kind of hype, but good with having a comprehensive vision of computing. Except that vision and its relation to finances had schizoaffective traits.
Same with DEC.
The point is to show “engagement”, “interest”, which they can then use to promise that down the line huge piles of money will fall out of this pinata.
Well. It’s not unprecedented for business opportunities to dry out. It’s actually normal. What’s more important, the investors supporting that are the dumber kind, and the investors investing in more real things are the smarter kind. So when these crash (for a few years hunger will probably become a real issue not just in developing countries when that happens), those preserving power will tend to be rather insightful people.
If only Sun survived till now, I feel they would have good days
The problem is a lot of what Sun brought to the industry is now in the Linux arena. If Sun survived, would Linux have happened? With such a huge development infrastructure around Linux, would Sun really add value?
I was a huge fan of Sun also, they revolutionized the industry far above their footprint. However their approach seemed more research or academic at times, and didn’t really work with their business model. Red Hat figured out a balance where they could develop opensource while making enough to support their business. The Linux world figured out a different balance where the industry is above and beyond individual companies and doesn’t require profit
The problem is a lot of what Sun brought to the industry is now in the Linux arena. If Sun survived, would Linux have happened? With such a huge development infrastructure around Linux, would Sun really add value?
Linux is not better than Solaris. It was, however, circumstantially more affordable, more attractive, and more exciting than Solaris at the same time. They’ve made a lot of strategic mistakes, but those were in the context of having some vision.
I mean this to say that the “huge development infrastructure around Linux” is bigger, but much less efficient than that of any of BSDs, and than that of Solaris in the past. Linux people back then would take pride in ability to assemble bigger resources, albeit with smaller efficiency, and call that “the cathedral vs the bazaar”, where Linux is the bazaar. Well, by now one can see that the bazaar approach make development costs bigger long-term.
IMHO if Sun didn’t make those mistakes, Solaris would be the most prestigious Unix and Unix-like system, but those systems would be targeted by developers similarly. So Linux would be alive, but not much more or less popular than FreeBSD. I don’t think they’d need Solaris to defeat all other Unix systems. After all, in early 00s FreeBSD had SVR4 binary compatibility code, similarly to its Linux compatibility code, which is still there and widely used. Probably commercial software distributed in binaries would be compiled for that, but would run on all of them. Or maybe not.
It’s hard to say.
But this
The Linux world figured out a different balance where the industry is above and beyond individual companies and doesn’t require profit
is wrong, everything about Linux that keeps going now is very commercial. Maybe 10 years ago one could say it’s not all about profit.
The point is the industry is not a profit driven entity, but has room for many profit driven entities.
That’s like saying your body is not a protein driven mechanism (cause there are many other things involved), but has room for proteins.
If somebody tears out half of your internal organs, you die.
If profit-driven companies stop participating in Linux, Linux dies. Today’s Linux. Linux of year 1999 wouldn’t.
That’s how even gifts can be the needle to control you.
I mean, why is this even a point of contention. BSDs played safe in terms of politics, Linux gambled by not considering the dangers. BSDs grew more slowly, Linux took the bank. But now Linux is confined by the decisions made back then. BSDs are more free.
I understand some of the hype. LLMs are pretty amazing nowadays (though closedai is unethical af so don’t use them).
I need to program complex cryptography code for university. Claude sonnet 3.5 solves some of the challenges instantly.
And it’s not trivial stuff, but things like “how do I divide polynomials, where each coefficient of that polynomial is an element of GF(2^128).” Given the context (my source code), it adds it seamlessly, writes unit tests, and it just works. (That is important for AES-GCM, the thing TLS relies on most of the time .)
Besides that, LLMs are good at what I call moving words around. Writing cute little short stories in fictional worlds given some info material, or checking for spelling, or re-formulating a message into a very diplomatic nice message, so on.
On the other side, it’s often complete BS shoehorning LLMs into things, because “AI cool word line go up”.
“Built to do my art and writing so I can do my laundry and dishes” – Embodied agents is where the real value is. The chatbots are just fancy tech demos that folks started selling because people were buying.
Though the image generators are actually good. The visual arts will never be the same after this
Compare it to the microwave. Is it good at something, yes. But if you shoot your fucking turkey in it at Thanksgiving and expect good results, you’re ignorant of how it works. Most people are expecting language models to do shit that aren’t meant to. Most of it isn’t new technology but old tech that people slapped a label on as well. I wasn’t playing Soul Caliber on the Dreamcast against AI openents… Yet now they are called AI opponents with no requirements to be different. GoldenEye on N64 was man VS AI. Madden 1995… AI. “Where did this AI boom come from!”
Marketing and mislabeling. Online classes, call it AI. Photo editors, call it AI.
I wasn’t playing Soul Caliber on the Dreamcast against AI openents…
Maybe terminology differs by region, but I absolutely played against AI as a kid. When I set up a game of Command and Conquer or something, I’d pick the number of AI opponents. Sometimes we’d call them bots (more common in FPS) or “the computer” or “CPU” (esp in Civ and other TBS), but I distinctly remember calling RTS SP opponents “AI” and I think many games used that terminology during the 90s.
What frustrates me is the opposite of what you’re saying, people have changed the meaning of “AI” from a human programmed opponent to a statistical model. When I played against “AI” 20-30 years ago, I was playing against something a human crafted and tuned. These days, I don’t play against “AI” because “AI” generates text, images, and video from a statistical model and can’t really play games. AI is something that runs in the cloud, with maybe a small portion on phones and Windows computers to do simple tasks where the network would add too much latency.
Sometimes I really regret having signed onto an instance that disables downvotes.
It’s easy to switch.
That said, I think the comment is constructive. It used to be that websites, textbooks, etc would pay artists or pay for stock photos (which indirectly pays artists), but now they can gen a dozen or so images and pick their favorite.
I’m not saying this is good or bad, but I do agree that art will never be the same.
I’ve been thinking about this a lot recently. No, we’re not there yet, may never be. Compare what Jesar, one of my favorite artists, can do - and that was in the oh-so-long-ago 2000s - and what an AI can do. It’s simply not up to the task. I do use AI a lot to create what is basically utility art. But it depends on pre-defined textual or visual inputs whereas only an artist can have divine inspiration. AI is more of a sterile tool, like interactive clipart, if you will.
I think “interactive clipart” is a great description. You are, I believe, totally correct that (at least for now) GenAI can’t do what professionals can do, but it can do better than many / most non-professionals. I can’t do art to save my life, and I don’t have the money to pay pros to make the mundane, boring everyday things that I need (like simple, uncluttered pictures for vocabulary cards). GenAI solves that problem for me.
Similarly, teachers used to try to rewrite complex texts for students at lower reading levels (such as English Learners). That took time and some expertise. Now, GenAI does it prolly many tens of thousands of times a day for teachers all over the USA.
I think, at least for the moment, that middle / lower level is where GenAI is currently most helpful - exactly the places that, in earlier times, were happy with clipart.
At a beach restaurant the other night I kept hearing a loud American voice cut across all conversation, going on and on about “AI” and how it would get into all human “workflows” (new buzzword?). His confidence and loudness was only matched by his obvious lack of understanding of how LLMs actually work.
“Confidently incorrect” I think describes a lot of AI aficionados.
And LLMs themselves.
I would also add “hopeful delusionals” and “unhinged cultist” to that list of labels.
Seriously, we have people right now making their plans for what they’re going to do with their lives once Artificial Super Intelligence emerges and changes the entire world to some kind of post-scarcity, Star-Trek world where literally everyone is wealthy and nobody has to work. They think this is only several years away. Not a tiny number either, and they exist on a broad spectrum.
Our species is so desperate for help from beyond, a savior that will change the current status-quo. We’ve been making fantasies and stories to indulge this desire for millenia and this is just the latest incarnation.
No company on Earth is going to develop any kind of machine or tool that will destabilize the economic markets of our capitalist world. A LOT has to change before anyone will even dream of upending centuries of wealth-building.
AI itself too i guess. Also i have to point this out every time but my username was chosen way before all this shit blew up into our faces. Ive used this one on every platform for years.
Some people can only hear “AI means I can pay people less/get rid of them entirely” and stop listening.
AI means C level jobs should be on the block as well. The board can make decisions based on their output.
The whole ex-Mckinsey management layer is at risk. Whole teams of people who were dedicated to producing pretty slides with “action titles” for managers higher up the chain to consume and regurgitate are now having their lunch eaten by AI.
Just wait until Elon puts AI in those new robots he invented!!!
/s for those who need it…
I’ve noticed that the people most vocal about wanting to use AI get very coy when you ask them what it should actually do.
I also notice the ONLY people who can offer firsthand reports how it’s actually useful in any way are in a very, very narrow niche.
Basically, if you’re not a programmer, and even then a very select set of programmers, then your life is completely unimpacted by generative AI broadly. (Not counting the millions of students who used it to write papers for them.)
AI is currently one of those solutions in search of a problem. In its current state, it can’t really do anything useful broadly. It can make your written work sound more professional and at the same time, more mediocre. It can generate very convincing pictures if you invest enough time into trying to decode the best sequence of prompts and literally just get lucky, but it’s far too inacurate and inconsistent to generate say, a fully illustrated comic book or cartoon, unless you already have a lot of talent in that field. I have tried many times to use AI in my current job to analyze PDF documents and spreadsheets and it’s still completely unable to do work that requires mathematics as well as contextual understanding of what that math represents.
You can have really fun or cool conversations with it, but it’s not exactly captivating. It is also wildly inaccurate for daily use. I ask it for help finding songs by describing the lyrics and other clues, and it confidentially points me to non-existing albums by hallucinated artists.
I have no doubt in time it’s going to radically change our world, but that time frame is going to require a LOT more time and baking before it’s done. Despite how excited a few select people are, nothing is changing overnight. We’re going to have a century-long “singularity” and won’t realize we’ve been through it until it’s done. As history tends to go.
"AI, how do I do in "
"Here is some code. Please fix any errors: "
These save me hours of work on a regular basis and I don’t even use the paid tier of ChatGPT for it. Especially the first one because I used to read half the documentation to answer that question. Results are accurate 80% of the time, and the other 20% is close enough that I can fix it in a few minutes. I’m not in an obscure AI related field, any programmer can benefit from stuff like this.
This is literally the only field in which anyone says it’s helpful, and I have made effort to reach out to users to see if it’s really helping. And even then, about half the programmers I’ve talked to about it (out of maybe a dozen) say that it’s either useless for their particular field of coding, or extremely hit-or-miss, it’s more like a quick dice-roll to see if the thing gives them something useful.
Because as a social phenomenon it promises to decide for them what it should actually do.
Porn / ai gf. Thats what 90% of ai power users do.
I really like the idea of an LLM being narrowly configured to filter, summarize data which comes in at a irregular/organic form.
You would have to do it multiples in parallel with different models and slightly different configurations to reduce hallucinations (Similar to sensor redundancies in Industrial Safety Levels) but still, … that alone is a game changer in “parsing the real world” … that energy amount needed to do this “right >= 3x” is cut short by removing the safety and redundancy because the hallucinations only become apparent down the line somewhere and only sometimes.
They poison their own well because they jump directly to the enshittyfication stage.
So people talking about embedding it into workflow… hi… here I am! =D
A buddy of mine has been doing this for months. As a manager, his first use case was summarizing the statuses of his team into a team status. Arguably hallucinations aren’t critical
I would argue that this makes the process microscopically more efficient and macroscopically way less efficient. That whole process probably is useless, and imagine wasting so much energy, water and computing power just to speed this useless process up and saving a handful of minutes (I am a lead and it takes me 2/3 minutes to put together a status of my team, and I don’t usually even request a status from each member).
I keep saying this to everyone in my company who pushes for LLMs for administrative tasks: if you feel like LLMs can do this task, we should stop doing it at all because it means we are just going through the motions and pleasing a process without purpose. You will have people producing reports via LLM from a one-line prompt, the manager assembling it together with LLM and at vest someone reading it distilling it once again with LLMs. It is all a great waste of money, energy, time, cognitive effort that doesn’t benefit anybody.
As soon as someone proposes to introduce LLMs in a process, raise with cutting that process altogether. Let’s produce less bullshit, instead of more while polluting even more in the process.
But the line must go up!
The article does mention that when the AI bubble is going down, the big players will use the defunct AI infrastructure and add it to their cloud business to get more of the market that way and, in the end, make the line go up.
That’s not what the article says.
They’re arguing that AI hype is being used as a way of driving customers towards cloud infrastructure over on-prem. Once a company makes that choice, it’s very hard to get them to go back.
They’re not saying that AI infrastructure specifically can be repurposed, just that in general these companies will get some extra cloud business out of the situation.
AI infrastructure is highly specialized, and much like ASICs for the blockchain nonsense, will be somewhere between “very hard” and “impossible” to repurpose.
Assuming a large decline in demand for AI compute, what would be the use cases for renting out older AI compute hardware on the cloud? Where would the demand come from? Prices would also go down with a decrease in demand.
Relaunching Stadia?
Haha. I believe the AMD Instinct / Nvidia Datacentre GPUs aren’t that great for gaming.
So you’re saying we wont have any crowdsourced blockchain Web 2.0 AIs?
Quantum! don’t forget quantum, you filthy peasant.
Please, stay with the time. We’re at Web 6.0 already.
Where’s my federated open source AI that runs on Linux 😤
The drones doing airstrikes might!
Big tech is out of ideas and needs AI to work in order to drive growth.
oh wow who would have guessed that business consultancy companies are generally built on bullshitting about things which they dont really have a grasp of
Education is one area where GenAI is having a huge impact. Teachers work with text and language all day long. They have too much to do and not enough time to do it. Ideally, for example, they should “differentiate” for EACH and EVERY student. Of course that almost never happens, but second best is to differentiate for specific groups - students with IEPs (special ed), English Learners, maybe advanced / gifted.
More tech aware teachers are now using ChatGPT and friends to help them do this. They are (usually) subject area experts, so they can quickly read through a generated or modified text and fix or remove errors - hallucinations are less (ime) of an issue in this situation. Now, instead of one reading that only a few students can actually understand, they have three at different levels, each with their own DOK questions.
People have started saying “AI won’t replace teachers. Teachers who use AI will replace teachers who don’t.”
Of course, it will be interesting to see what happens when VC funding dries up, and the AI companies can’t afford to lose money on every single interaction. Like with everything else in USA education, better off districts may be able to afford AI, and less-well-off (aka black / brown / poor) districts may not be able to.
Bye bye XBox ._.
Page doesn’t render properly.
I saved a lot of time due to ChatGPT. Need to sign up some of my pupils for a competition by uploading their data in a csv-File to some plattform? Just copy and paste their data into chsatgpt and prompt it to create the file. The boss (headmaster) wants some reasoning why I need some paid time for certain projects? Let ChatGPT do the reasoning. Need some exercises for one of my classes that doesn’t really come to grips with while-loops? let ChatGPT create those exercises (some smartasses will of course have ChatGPT then solve those exercises). The list goes on…
Just copy and paste [student personal data] into [3rd parties database]
Yeah, that’s a problem, especially in Europe. Im unsure about US, but it’s definitely a breach of GDPR.
You are an asshole if you’re uploading student data to a mining operation.
Well, I hope the data protection official of my school won’t find out. Oh wait, shit. He did find out. It’s me and idgaf.
I just want you to know that actual scientists have morals. You are not a scientist and I’m coming to replace you.
Where do you work?
Yeah, and Wikipedia is one of the most useful sites on the net, but it didn’t exactly result in the entire web becoming crowdsourced.
ChatGPT is basically like a really good intern, and I use it heavily that way. I run literally every email through it and say “respond to so and so, say xyz” and then maybe a little refining, copy paste, done.
The other day, my boss sent me an excel file with a shitload of data in it that he wanted me to analyze some such way. I just copy pasted it into gpt and asked it, and it spit out the correct response. Then my boss asked me to do something else that required a bit of excel finagling that I didn’t really know how to do, so i asked gpt, and it told me the formula, which worked immediately first try.
So basically it helps me accomplish tasks in seconds that previously would’ve taken hours. If anything, I think markets are currently undervalued, because remarkably, fucking NONE of my colleagues or friends are using it at all yet. Once there’s widespread adoption, which will pretty much have to happen if anyone wants to stay competitive once it gains more traction, look out…
That also is my experience.
The poem about AI that often gets posted says “What are you trying to avoid? The living [of a life]?”
And yeah, that’s what it’s for, dodging shit you don’t want to do. I gotta produce some useless bullshit that no one’s going to read or care about: AI.
I don’t even mind AI art for things like LinkedIn posts, blogs like “What is warehouse management?” or “Top 10 finance trends in 2025” - SEO spam that no human will read. No one wants to write it, read it, or care about it- its just a x kb file to tell Google to look here.
Those pupils will really thank you when they grow up and there isn’t enough fresh water because all the data centres are using it up far faster than it can be replenished.
https://utulsa.edu/news/data-centers-draining-resources-in-water-stressed-communities/
The thing about tech bubbles is everyone rushes in full bore, on the hope that they can be the ones whose moonshot goes the distance. However even in the case where the technology achieves all its promise, most of those early attempts will not. Soon enough, we’ll be down to the top few, and only their datacenters will need to exist. Many of these failures will go away
Many of these failures will go away
In a rational, non-capitalist world, yes. In our world, all of those data centres will last until they can’t find a way to squeeze some sort of profit out of them.
One time, I needed to convince my boss’s boss that we needed to do something, and he wanted it in writing. Guess who wrote the proposal? And far more eloquently than I could have alone, in the time allowed. It required some good prompts, attentive proofreading, and a few drafts. But in the end, it was quite effective.
I have no idea how people can consider this to be a hype bubble especially after the o3 release. It smashed the ARC AGI benchmark on the performance front. It ranks as the 175th best competitive coder in the world on Codeforces’ leaderboard.
o3 proved that it is possible to have at least an expert AGI if not a Virtuoso AGI (according to Deep mind’s definition of AGI). Sure, it’s not economical yet. But it will get there very soon (just like how the earlier GPTs were a lot dumber and took a lot more energy than the newer, smaller parameter models).
Please remember - fight to seize the means of production. Do not fight the means of production themselves.
It’s a bubble because OpenAI spend $2.35 for every $1.00 they make. Yes, you’re mathing right, that is a net loss.
It’s a bubble because all of the big players in AI development agree that future models will cost exponentially more money to train, for incremental gains. That means there is no path forward that doesn’t intensely amplify the unprofitability of an already deeply unprofitable industry.
It’s a bubble because newer models with better capabilities only cost more and more to run.
It’s a bubble because as far as anyone knows there will never be a solution to the hallucination problem.
It’s a bubble because despite investments treating it as a trillion dollar industry, no one has yet figured out a trillion dollar problem that AI can solve.
You’re trying on a new top of the line VR headset and saying “Wow, this is incredible, how can anyone say this is a bubble?” Its not about how cool the tech is in isolation, it’s about its potential to effect widespread change. Facebook went in hard on VR, imagining a future where everyone worked from home while wearing VR headsets. But what they got was an expensive toy that only had niche uses.
AI performs do well on certain coding tasks because a lot of the individual problems that make up a particular piece of software have already been solved. It’s standard practice to design programs as individual units, each of which performs the smallest task possible, and which can then be assembled to complete more complex tasks. This fits very well into the LLM model of assembling pieces into their most likely expected configurations. But it cannot create truly novel code, except by a kind of trial and error mutation process. It cannot problem solve. It cannot identify a users needs and come up with ideal solutions to them. It cannot innovate.
This means that, at best, genAI in the software world becomes a tool for producing individual code elements, guided and shepherded by experienced programmers. It does not replace the software industry, merely augments it, and it does so at a cost that many companies simply may not feel is worth paying.
And that’s its best case scenario. In every other industry AI has been a spectacular failure. But it’s being invested in as if it will be a technological reckoning for every form of intellectual labour on earth. That is the absolute definition of a bubble.
o3 made the high score on ARC through brute force, not by being good. To raise the score from 75% to 87% required 175 times more computing power, but exactly stunning returns.
Why does it matter?
If it can through brute force, it can do it. That’s the first step towards true agi, nobody said the first AGI would be economical, this feels like a major goalpost shift if you’re acknowledging it can do it at all, isn’t that insane?
A little bit ago, everyone would’ve been saying this will never happen, that there was a natural wall simply because all it does is predict the next token, it’s been like, a few years of llm’s and they’re already getting this insane. We’re going to have AGI soon, it might not be a transformer, but billions upon billions of dollars are being thrown at this problem, there are people smart enough in the world to make this work, and this is the earliest sign that it’s coming.
I’m not convinced that it’s anywhere near an AGI, I’m convinced after combing through papers and code, that it’s an amazing parlor trick.
I’d love to be proven wrong, but everything I’ve seen and everything I’ve used in my studies ( using DNN to simulate neurodivergence and spinal disgenesis, which is kinda AI adjacent) leads me to believe that the current part won’t lead to anything but convincing parlor tricks.
The argument could be made that if a trick is convincing enough, does it matter if it’s intelligent or not.
What would convince you?
I’m not entirely sure.
A non-probabilistic algorithm, probably. Something that didn’t rely on the liklihood of association, and instead was capable of context and rationality.
Something that wouldn’t have a system capable of saying “Put glue on your pizza” because it would know that’s a silly thing to say to a human. A system that, when asked "Whats a good caustic detergent " wouldn’t be able to respond "Any good caustic detergent is a good caustic detergent " because duh. Something that doesn’t require thousands of hours of training to update and instead is capable of ingesting and rationalize new information on the fly.You’re probablistic, you just have an internal verifier, you think things that are silly, and then decide not to say them all the time. A human being often thinks things that they realize are silly before they say them… that’s an entirely unfair goal in the first place from my perspective, why does it have to be non-probablistic?
Are you not a general intelligence because sometimes your brain thinks silly things?
o3 currently works precisely that way, by the way, it generates hundreds of possible things, and then uses something that checks if the steps actually work, before it outputs. In fact, they then reinforce it on these correct logical steps, so it becomes better at not outputting illogical answers like you said.
it’s interesting that you said “not on the probability of the next word, but on context and rationality”
context IS pricesely that, you know what’s likely to come next because of the context, that’s you understanding context. YOU as a human being don’t even always get this right, you must realize we are not perfect beings, we think of possibilities and choose the right one. I think we’re much better at this right now, but i don’t think that’s a fundamental difference between us and o3.
Rationality is the internal verifier.
Something that doesn’t require thousands of hours of training to update and instead is capable of ingesting and rationalize new information on the fly.
Being able to do this is… exactly what arc-agi was testing. Literally the entire point of the benchmark, it can do that.
I’ve done the test by the way, I solved it by brute forcing possible solutions in my head, then checking if they were true… did you just divine the answers instantly?
Where, in that position piece, do they mention o3? Who “proved” this?
Additionally, I’m pretty sure that this “ARC AGI” benchmark is not using the same definition of AGI that you linked to by DeepMind. Conflating them is misleading. There is already so much misinformation out there about “AI”, don’t add to it.
Lastly, I struggle to take at face value essays written by for-profit companies claiming they have AGI (that DeepMind paper links to OpenAI essays). They only stand to gain monetarily by claiming that their AI is an AGI (to be clear, this is an opinion; I do not have evidence to suggest that OpenAI is being disingenuous).
Unless we invent cold fusion between the next 5 years, they will never be economical. They are the most energy inefficient thing ever invented by humanity and all prediction models state that it will cost more energy, not less, to keep making them better. They will never be energy efficient nor economical in their current state, and most companies are out of ideas on how to shake it up. Even the people who created generative models agree that they have just been brute forcing by making the models larger with more energy consumption. When you try to make them smaller or more energy efficient, they fall off the performance cliff and only produce garbage. I’m sure there are researchers doing cool stuff, but it is neither economical nor efficient.
Untrue. There are small models that produce better output than the previous “flagships” like GPT-2. Also, you can achieve much more than we currently do with far less energy by working on novel, specialised hardware (neuromorphic computing).
Your example is strange because, as far as I know, GPTs aren’t economical either.
Why is it getting an AGI stamp now? I was under the impression humanity has not delivered a sentient AI? Which is what the AGI title was supposed to be used for…has that been pulled back again?
Agi has nothing to do with sentience, which cannot be measured, openai, I think validly, defines it as a system that can do all intellectual labor.
So it’s now, can it do anything a human can do?..sans emotional traits.
It was never about sentience, sentience is a meaningless, unmeasurable term.
It’s a question of if it can replace humans in the workforce.
artificial general intelligence means it’s able to generalize its intelligence, not sentience at all.
“Today’s hype will have lasting effects that constrain tomorrow’s possibilities.”
Nope. No it won’t. I’d love to have the patience to be more diplomatic but they’re just wrong… and dumb.
I’m getting so sick of these anti AI cultists who seem to be made up of grumpy tech nerds behaving like “I was using AI before it was cool” hipsters and panicking artists and writers. Everyone needs to calm their tits right down. AI isn’t going anywhere. It’s giving creative and executive options to millions of people that just weren’t there before.
We’re in an adjustment phase right now and boundaries are being re-drawn around what constitutes creativity. My leading theory at the moment is that we’ll all mostly eventually settle down to the idea that AI is just a tool. Once we’re used to it and less starry eyed about it’s output then individual creativity, possibly supported by AI tools, will flourish again. It’s going to come down to the question of whether you prefer reading something cogitated, written, drawn or motion rendered by AI or you enjoy the perspective of a human being more. Both will be true in different scenarios I expect.
Honestly, I’ve had to nope out of quite a few forums and servers permanently now because all they do in there is circlejerk about the death of AI. Like this one theory that keeps popping up that image generating AI specifically is inevitably going to collapse in on itself and stop producing quality images. The reverse is so obviously true but they just don’t want to see it. Otherwise smart people are just being so stubborn with this and it’s, quite frankly, depressing to see.
Also, the tech nerds arguing that AI is just a fancy word and pixel regurgitating engine and that we’ll never have an AGI are probably the same people that were really hoping Data would be classified as a sentient lifeform when Bruce Maddox wanted to dissassemble him in “The Measure of a Man”.
How’s that for whiplash?
Models are not improving, companies are still largely (massively) unprofitable, the tech has a very high environmental impact (and demand) and not a solid business case has been found so far (despite very large investments) after 2 years.
That AI isn’t going anywhere is possible, but LLM-based tools might also simply follow crypto, VR, metaverses and the other tech “revolutions” that were just hyped and that ended nowhere. I can’t say it will go one way or another, but I disagree with you about “adjustment period”. I think generative AI is cool and fun, but it’s a toy. If companies don’t make money with it, they will eventually stop investing into it.
Also
Today’s hype will have lasting effects that constrain tomorrow’s possibilities
Is absolutely true. Wasting capital (human and economic) on something means that it won’t be used for something else instead. This is especially true now that it’s so hard to get investments for any other business. If all the money right now goes into AI, and IF this turns out to be just hype, we just collectively lost 2, 4, 10 years of research and investments on other areas (for example, environment protection). I am really curious about what makes you think that that sentence is false and stupid.
Models are not improving? Since when? Last week? Newer models have been scoring higher and higher in both objective and subjective blind tests consistently. This sounds like the kind of delusional anti-AI shit that the OP was talking about. I mean, holy shit, to try to pass off “models aren’t improving” with a straight face.
There is a bunch of research showing that model improvement is marginal compared to energy demand and/or amount of training data. OpenAI itself ~1 month ago mentioned that they are seeing a smaller improvements in Orion (I believe) vs GPT4 than there was between GPT 4 and 3. We are also running out of quality data to use for training.
Essentially what I mean is that the big improvements we have seen in the past seem to be over, now improving a little cost a lot. Considering that the costs are exorbitant and the difference small enough, it’s not impossible to imagine that companies will eventually give up if they can’t monetize this stuff.
Compare Llama 1 to the current state of the art local AI’s. They’re on a completely different level.
Yes, because at the beginning there was tons of room for improvement.
I mean take openAI word for it: chatGPT 5 is not seeing improvement compared to 4 as much as 4 to 3, and it’s costing a fortune and taking forever. Logarithmic curve, it seems. Also if we run out of data to train, that’s it.
Surely you can see there is a difference between marginal improvement with respect to energy and not improving.
Yes, I see the difference as in hitting the logarithmic tail that shows we are close to the limit. I also realize that exponential cost is a defacto limit on improvement. If improving again for chatGPT7 will cost 10 trillions, I don’t think it will ever happen, right?
It’s fucking fantastic news, tbh.
Here’s my take, let them dismiss it.
Let em! Remember Bitcoin at $15k after 2019?
Let em! And it’s justified! If Ai isn’t important right now, then why should its price be inflated to oblivion? Let it fall. Good! Lower prices for those of us that do see the value down the road.
That’s how speculative investment works. In no way is this bad. Are sales bad? Sit back and enjoy the show.
Are sales bad?
Of AI products? By all available metrics, yes, sales for AI driven products are atrocious.
Even the biggest name in AI is desperately unprofitable. OpenAI has only succeeded in converting 3% of their free users to paid users. To put that on perspective, 40% of regular Spotify users are on premium plans.
And those paid plans don’t even cover what it costs to run the service for those users. Currently OpenAI are intending to double their subscription costs over the next five years, and that still won’t be enough to make their service profitable. And that’s assuming that they don’t lose subscribers over those increased costs. When their conversion rate at their current price is only 3%, there’s not exactly an obvious appetite to pay more for the same thing.
And that’s the headline name. The key driver of the industry. And the numbers are just as bad everywhere else you look, either terrible, or deliberately obfuscated (remember, these companies sank billions of capex into this; if sales were good they’d be talking very openly and clearly about just how good they are).
That’s if you’re still in the camp that climate change isn’t politically impossible.
at least at this point
If I were more positive about the situation, I’d agree entirely, but… I don’t think we’re gonna make it, man.
