Users of OpenAI’s GPT-4 are complaining that the AI model is performing worse lately. Industry insiders say a redesign of GPT-4 could be to blame.
This isn’t sustainable. They’re banking that nobody else is going to be able to achieve GPT-4-like quality, and what with us basically being at near the bottom of the vertical bit of the growth curve, I’d say that’s a little like betting that nobody’s going to be able to build a car that beats the Model T’s performance. Meta is trying to tackle very large language models in the same way that they got React to be so good and widely supported: by taking it open source. Google, on the other hand, is currently working on having LLMs running natively on phones and tablets. That’s not to speak of the fully open source models. Yeah, running a 1.6 trillion parameter GPT-based LLM is fucking expensive and difficult to replicate, but there are newer, more efficient techniques popping up around LLMs at a dizzying pace. It’s only a matter of time before someone comes up with something that’s at least as good as GPT 4.
A popular venture capital backed tech project with an unsustainable business model? Now Ive heard everything. /s
Good, they should be seperate.
You don’t want a medical llm trained on Internet memes or a coding llm trained to write poetry. Specialisation exists for a reason.
Honest question, why would you want a medical LLM anyway? Other kinds of AI, sure, like diagnosis help through pattern learning on medical imaging, etc, that I can understand.
How is a language based approach that completely abstracts away actual knowledge, and just tries to sound “good enough” any kind of useful in a medical workflow?
How is a language based approach that completely abstracts away actual knowledge, and just tries to sound “good enough” any kind of useful in a medical workflow?
A LLM cross-referencing a list of symptoms against papers and books could be helpful for example. There is so much medical literature available these days and in so many languages that no one person can hope to gain a somewhat clear overview, much less keep up with all the new stuff coming out.
Of course this should only be in assistance to a trained medical professional, as all neural networks are prone to hallucinations. You should also double-check results of NNs that interpret medical images, they may straight-up hallucinate or just pick up on correlation instead of causation (say all the cancer images in your training set having a watermark from the same lab or equipment manufacturer).
I work in the assisted living field. There’s frequently 1 nurse tending 40+ beds for 8 hours. If the next nurse is late, that’s 1 nurse for 8+ hours until the next one shows. You can bet your ass that nurse isn’t providing high quality medical advice 12 hours into a shift. An ai can take a non partial perspective and output a baseline level of advice to help the wheels moving.
A lot of people in the media are routinely confused about the different between AI and ordinary software. They are started to call all software “AI” now.
Can you quantify the difference? Far as I can tell, there’s just an imaginary line where software becomes AI just because the logic filtering it depends on to operate is sufficiently complex. The term doesn’t really seem to be a useful categorization either, e.g. the fundamentally different approaches of diffusion models and transformer models.
But the only thing it’s actually good at is generating languages, if they try and pretend to know stuff in fields, they’re quickly exposed as frauds.
Ah, yes, when I was a kid, I would try to read big texts I understood nothing of and imitate something similar. I thought it made me smarter.
In some sense it did - probabilities of certain words being connected in a certain way, if you make some connection between them and real entities, are useful.
I mean, it did work at school, just say some water without turning on your brain. I sometimes start talking like this when I panic after a question.
I cant express my diappointment with chatgpt, they let loose a bot that makes content farms shreek in joy but messes up basic things if their is no well treaded answer, wont give you non mainstream answers (you likely already know and watched what it tells you is “really obscure anime”) And jenuinely has no tolerance for error, from you or itself
It doesn’t even “know” language. Every time I see it write a poem it reads like something a 3rd grader would come up with. At the end of the day, language is way to explain your experience. An LLM doesn’t have experiences.
yeah this makes more sense. companys arent just going to buy a licence to GPT-6 and replace 80% of their staff from an off the shelf solution, rather I expect AI’s will be trained specifically within certain industries and tasks and drive efficiencies
The model has become inbred because it’s now impossible to scrape the web without AI content getting ingested, which is full of “hallucinations” and other weird artifacts. The last opportunity to get “uncontaminated” training data was sometime in mid 2022.
Not to say that it’s causing this particular problem, but this issue will emerge eventually. Garbage in = garbage out. Eventually GPT-19 will grow a mighty Habsburg chin.
Maybe not yet, but…
- Spez will turn Reddit into a bot farm and sell this as training data
- Musk turns Twitter into a bigoted cesspool and will sell this as training data, which will subsequently be flagged for low quality (also: a botfarm)
- Threads is a corporate ad dashboard (and we already know how easy it is to GPT copy) and Zuck will sell this as training data
- Facebook is either dead or only good for boomers and Poles
- blogs are dead
- Fediverse is out there waiting to be scraped but possibly too small to sustain a big model
We’te getting there, hopefully.
…is Facebook popular with Polish people? Or was this a weird polish joke I don’t get?
Very. Twitter never took off among general population (only politicians, journalists, botfarms and people who troll politicians and journalists), tiktok is for kids, Instagram is popular but again, rather among influencers and people who need to show off pictures not as a default SM app. I don’t really know where did Americans and west Europeans move from Facebook.
All the articles with very specific titles, but then incredibly generic content, piss me off to no end.
Part of the reason why debugging windows is such a pain. Another part is the so called experts in the forums.
I suspect future models are going to have to put some more focus on learning using techniques more like what humans use, and on cognition.
Like, compared to a human these language models need very large quantities of text input. When humans are first learning language they get lots of visual input along with language input, and can test their understanding with trial-and-error feedback from other intelligent actors. I wonder if perhaps those factors greatly increase the rate at which understanding develops.
Also, humans tend to cogitate on inputs while ingesting them during learning. So if the information in new inputs disagrees with current understanding, those inputs are less likely to affect current understanding (there’s a whole ‘how to change your mind’ thing here that is necessary for people to use, but if we’re training a model on curated data that’s probably less important for early model training).
I don’t know details of how model training works, but it would be interesting to know if anyone is using a progressive learning technique where the model that is being trained is used to judge new training data before it is used as a training input to update the model’s weights. That would be kind of like how children learn by starting with very simple words and syntax and building up conceptual understanding gradually. I’d assume so, since it’s an obvious idea, but I haven’t heard about it.
For fun I asked ChatGPT about that progressive learning approach, and it seems to like the idea.
I wish I had more time to undertake some experiments in model training, this seems like it would be a really fun research direction.
Sorry for the ‘wall of AI text’:
The idea you’re describing seems to be a form of curriculum learning. In curriculum learning, models are trained in a progressive manner, starting with simple concepts (or in this case, simpler text data) and gradually moving to more complex ones. This approach is motivated by the way human learning often works, where we learn easier topics before moving on to harder ones.
The strategy you’ve suggested, where the model itself determines the complexity or understandability of the next round of training inputs, is interesting. While the traditional approach to curriculum learning is to manually design the learning progression based on human knowledge and intuition, the approach you’re suggesting is more dynamic and autonomous, letting the model guide its own learning process.
As of my last update in September 2021, I can’t confirm any specific projects or papers that have employed exactly this strategy in the domain of large language models. However, there are some related works in the field. For example, some reinforcement learning and computer vision projects have used a similar idea where models adaptively choose their next training samples based on their current understanding. This has been referred to as active learning, and is a promising avenue for improving the efficiency of model training.
However, there would be several technical challenges in applying this approach to large language models. For one, there would be the challenge of how to assess the “understandability” of a text sample in a reliable and useful way. This would likely require significant work to define and might also have to involve some form of reinforcement learning or other feedback mechanisms. Nonetheless, it’s a fascinating idea and could potentially be an interesting direction for future research in machine learning.
The lobotomies will continue. Free models will keep getting better.
Not the first time OpenAI has done this. DALLE2 used to be the best AI art program in the world. Then OpenAI decided that they didn’t want to get sued by celebrities, so they made it so that if a face came out that resembled a celebrity, it would be distorted. But every face kind of looks like someone famous. Ta da! Now DALLE2 can’t do faces.
Want a crane shot areal image of a teen couple in a corvette driving off into the sunset? Well, you are now banned for life from the DALLE2 service, because DALLE2 produced an image of a ‘shot teen’ and that violates it’s terms of service.
The only way in mind this dumbing down happens is by fumbling with the model. So that’s the one thing we can be sure: the AI is most definitely changed while publicly staying “ChatGPT 4”. I assume they are either using clipping or token limitations to split the server load but fucking up the result, or they are purposely dumbing it down to capitalise on it later by introducing other pay models like ppl already mentioned.
Either way they are shooting themselves in the foot because a bunch of ppl will unsubscribe either out of spite for the change or because it’s just not worth it anymore for them.
I remember one time a guy was trying to add SDL (a programming library) to Visual Studio (code editor and IDE), and said that it wouldn’t link to a project no matter what he’s done. You can google how to do this in five minutes, with video tutorials and everything, it’s like a basic thing every programmer does in that IDE. Like 5 question threads later, turns out he was “following all ChatGPT steps” and they were all complete nonsense, just random functions of Visual Studio done with the filenames of SDL.
lmfao. Why haven’t most people figured out yet that chatgpt lies more often than not?
Might be right but in my experience a lack of skill in conversing with AI is a much greater factor in determining it’s usefulness. It’s almost always going to defer to the user. It’s like when someone is dealing with tech support and they tell them to try turning it off and on again. If that really is the solution, and the user insists that it is not, CGPT is going to make something up just to appease the user’s request.
Users have to know that CGPT isn’t magic. How they behave affects how it behaves. Kind of like talking to actual people, which is what it’s essentially trying to simulate.
