[email protected]

It’s really good at filling in gaps, or rearranging things, or aggregating data or finding patterns.

So if you need gaps filled, things rearranged, data aggregated or patterns found: AI is useful.

And that’s just what this one, dumb guy knows. Someone smarter can probably provide way more uses.

I don’t think the comparison with crypto is fair.

People are actually using these models in their daily lives.

Yes, community list: lemmy.intai.tech/post/2182

LLM’s are extremely flexible and capable encoding engines with emergent properties.

I wouldn’t bank on them “replacing all software” soon but they are quickly moving into areas where classic Turing code just would not scale easily, usually due to complexity/maintainance.

Yes. What a strange question…as if hivemind fads are somehow relevant to the merits of a technology.

There are plenty of useful, novel applications for AI just like there are PLENTY of useful, novel applications for crypto. Just because the hivemind has turned to a new fad in technology doesn’t mean that actual, intelligent people just stop using these novel technologies. There are legitimate use-cases for both AI and crypto. Degenerate gamblers and Do Kwan/SBF just caused a pendulum swing on crypto…nothing changed about the technology. It’s just that the public has had their opinions shifted temporarily.

It is extremely useful in the right circumstances. When people say it isn’t useful or that it’s ‘stupid’, they’re not looking at the proper use cases - every tool has good and bad ways to use it (you wouldn’t use a hammer to peel an apple).

For example, we will soon have fully rendered smoke simulated at real time in 3D spaces (ie. video games) because we can calculate a small portion of how that smoke looks and then have AI guess what the rest looks like (with shockingly good results!)

AI is not a fad, it’s not going away, it’s improving rapidly, and it is going to massively change our digital world within years.

Opinion source: a professional programmer, game developer, and someone that thoroughly despises cryptocurrency

AI is nothing like cryptocurrency. Cryptocurrencies didn’t solve any problems. We already use digital currencies and they’re very convenient.

AI has solved many problems we couldn’t solve before and it’s still new. I don’t doubt that AI will change the world. I believe 20 years from now, our society will be as dependent on AI as it is on the internet.

I have personally used it to automate some Excel stuff I do at work. I just described my sheet and what I wanted done and it gave me a block of code that did it. I had spent time previously looking stuff up on forums with no luck. My issue was too specific to my work that nobody seemed to have run into it before. One query to ChatGTP solved my issue perfectly in seconds, and that’s just a few online tool in its infancy.

I work at a small business and we use it to write out dumb social media post. I hated doing it before. Sometimes I’ll write it myself still and ask chatgpt to add all the relevant emojis. I also think ai had the chance to be what we’ve always wanted from Alexa, assistant, and Siri. Deep system integration with the os will allow it to actually do what we want it to do with way less restrictions. Also, try using chatgpts voice recognition in the app. It blows the one built into your phone out of the water.

We’ve been using it at my day job to help us outline ideas for our content writers. It writes garbage content on its own, but it is a decent tool for organizing ideas.

At least that is what we use it for. I’m sure there are other valuable uses, but it is not as valuable (to me at least) as it has been made out to be.

You could ask AI to find antibiotics to kill antibiotic resistant bacteria. The bonus would be to give it a lab and drones to conduct actual tests.

I will give you just one example. Pharmaceutical companies often create aggregate reports where they have to process a large number of cases. Say, 5000. Such processing sometimes includes analysis of x-Ray or other images. Very specialized and highly paid people (radiologists) do this. It is expensive and is part of the reason why medicine prices are high. One company recently had a trial - if AI can do that job. Turns out it can. Huge savings for the company. And the radiologist lost their job. This is just one example of good and bad things that will and already are happening in our society due to AI.

Yes and it should not be in a handful of companies and also be regulated up the ying yang. smartless.com/…/mit-professor-max-tegmark-live-in…

It is a useful tool to do something that I already know the answer but too lazy to work out. E.g. generate dummy data

First of all AI is a buzzword that’s meaning has changed a lot since at least the 1950s. So… what do you actually mean? If you mean LLM like ChatGPT, it’s not AGI that’s for sure. It is another tool that can be very useful. For coding, it’s great for getting you very large blocks of code prepopulated for you to polish and verify it does what you want. For writing, it’s useful to create a quick first draft. For fictional game senses it’s useful for “embedding a character quickly”, but again you likely want to edit it some even for say a D&D game.

I think it can replace most first line chat based customer service people, especially ones who already just make stuff up to say something to you (we all have been there). I could imagine it improving call routing if hooked into speech recognition and generation - the current menus act like you can “say anything” but really only “work” if you’re calling about stuff you could also do with simple press 1,2,3 menus. ChatGPT based things trained on the companies procedures and data probably could also replace that first line call queues because it can seem to more usefully do something with wider issues. Although companies still would need to get their head out of their asses somewhat too.

Where I’ve found it falls down currently is very specific technical questions, ones you might have asked on a forum and maybe gotten an answer. I hope it improves, especially as companies start to add some of their own training data. I could imagine Microsoft more usefully replacing the first few lines of tech support for their products, and eventually having the AI pass up the chain to a ticket if it can’t solve the issue. I could imagine in the next 10 years most tech companies having purchased a service from some AI company to provide them AI support bots like they currently pay for ticket systems and web hosting. And I think in general it probably will be better for the users, because for less than the cost of the cheapest outsourced front line support person (who has near 0 knowledge) you can have the AI provide pretty good chat based access to a given set of knowledge that is growing all the time, and every customer gets that AI with that knowledge base rather than the crap shoot of if you get the person who’s been there 3 years or 1 day.

I think we are a long way from having AI just write the program or CNC code or even important blog posts. The hallucination has to be fixed without breaking the usefulness of the model (people claim guardrails on GPT4 make it stupider), and the thing needs to recursively look at it’s output and run that through a “look for bugs” prompt followed by a “fix it” prompt at the very least. Right now, it can write code with noticeable bugs, you can tell it to check for bugs and it’ll find them, and then you can ask it to fix those bugs and it’ll at least try to do that. This kind of needs to be built in and automatic for any sort of process - like humans check their work, we need to program the AI to check it’s work too. And then we might need to also integrate multiple different models so “different eyes” see the code and sign off before being pushed. And even then, I think we’d need additional hooks, improvement, and test / simulation passes before we “don’t need human domain experts to deploy”. The thing is - it might be something we can solve in a few years with traditional integrations - or it might not be entirely possible with current LLM designs given the weirdness around guardrails. We just don’t know.

I've been using it at my job to help me write code, and it's a bit like having a soux chef. I can say "I need an if statement that checks these values" or "Give me loop that does x y and z" and it'll almost always spit out the right answer. So coding, at least most of the time, changes from avoiding syntax errors and verifying the exact right format and turns into asking for and assembling parts.

But the neat thing is that if you have a little experience with a language you can suddenly start writing a lot of code in it. I had to figure out something with Ansible with zero experience. ChatGPT helped me get a fully functioning Ansible deployment in a couple days. Without it I'd have spent weeks in StackOverflow and documentation trying to piece together the exact syntax.

I mean, AI can be used to design a lot of robust yet efficient structures. In engineering and architecture, with enough data, AI can generate designs for buildings, and parts that are not only sturdy but can be built with less resources along with other design considerations. There's a really cool nasa video where competitors are trying to 3D print structures for habitation in space.

AI is also used in medicine to come up with new protein structures to create new medicine. It's also used in environmental sciences, to help predict earthquakes or monitor land use, etc.

There's a lot of practical uses for AI.

Crypto and AI can’t be compared at all. One is an extremely useful and revolutionary tool. The other is just pump & dump ponzi schemes for libertarians.

AI has gone through several cycles of hype and winter. There's even a Wikipedia page for it: https://en.m.wikipedia.org/wiki/AI_winter

Of course it's valuable to discuss the dangers and inequities of a new technology. But one of the dangers is being misled.

Just because it’s ‘the hot new thing’ doesn’t mean it’s a fad or a bubble. It doesn’t not mean it’s those things, but…the internet was once the ‘hot new thing’ and it was both a bubble (completely overhyped at the time) and a real, tidal wave change to the way that people lived, worked, and played.

There are already several other outstanding comments, and I’m far from a prolific user of AI like some folks, but - it allows you to tap into some of the more impressive capabilities that computers have without knowing a programming language. The programming language is English, and if you can speak it or write it, AI can understand it and act on it. There are lots of edge cases, as others have mentioned below, where AI can come up with answers (by both the range and depth of its training data) where it’s seemingly breaking new ground. It’s not, of course - it’s putting together data points and synthesizing an output - but even if mechanically it’s 2 + 3 = 5, it’s really damned impressive if you don’t have the depth of training to know what 2 and 3 are.

Having said that, yes, there are some problematic components to AI (from my perspective, the source and composition of all that training data is the biggest one), and there are obviously use cases that are, if not problematic in and of themselves, at very least troubling. Using AI to generate child pornography would be one of the more obvious cases - it’s not exactly illegal, and no one is being harmed, but is it ethical? And the more societal concerns as well - there are human beings in a capitalist system who have trained their whole lives to be artists and writers and those skills are already tragically undervalued for the most part - do we really want to incentivize their total extermination? Are we, as human beings, okay with outsourcing artistic creation to this mechanical turk (the concept, not the Amazon service), and whether we are or we aren’t, what does it say about us as a species that we’re considering it?

The biggest practical reasons to not get too swept up with AI is that it’s limited in weird and not totally clearly understood ways. It ‘hallucinates’ data. Even when it doesn’t make something up, the first time that you run up against the edges of its capabilities, or it suggests code that doesn’t compile or an answer that is flat, provably wrong, or it says something crazy or incoherent or generates art that features humans with the wrong number of fingers or bodily horror or whatever…well then you realize that you should sort of treat AI like a brilliant but troubled and maybe drug addicted coworker. Man, there are some things that it is just spookily good at. But it needs a lot of oversight, because you can cross over from spookily good to what the fuck pretty quickly and completely without warning. ‘Modern’ AI is only different from previous AI systems (I remember chatting with Eliza in the primordial moments of the internet) because it maintains the illusion of knowing much, much better.

Baseless speculation: I think the first major legislation of AI models is going to be to require an understanding of the training data and ‘not safe’ uses - much like ingredient labels were a response to unethical food products and especially as cars grew in size, power, and complexity the government stepped in to regulate how, where, and why cars could be used, to protect users from themselves and also to protect everyone else from the users. There’s also, at some point, I think, going to be some major paradigm shifting about training data - there’s already rumblings, but the idea that data (including this post!) that was intended for consumption by other human beings at no charge could be consumed into an AI product and then commercialized on a grand scale, possibly even at the detriment of the person who created the data, is troubling.

I am super amateur with python and I don’t work in IT, but I’ve used it to write code for me that allows me to significantly save time in my work flow.

Like something that used to take me an hour to do now takes 15-20 minutes.

So as a nonprogrammer, im able to get it to write enough code that I can tweak until it works instead of just not having that tool.

As a professional editor, yeah, it’s wild what AI is doing in the industry. I’m not even talking about chatGPT script writing and such. I watched a demo of a tool for dubbing that added in the mouth movements as well.

They removed the mouth entirely from an English scene, fed it the line, and it generated not only the Chinese but generated a mouth to say it. It’s wild.

Who better to ask than ChatGPT itself. I threw your entire post at ChatGPT and here’s what it said:

As an AI language model, I can understand your skepticism and concerns regarding the hype surrounding AI. It’s true that both cryptocurrency and AI have been subjects of intense hype and speculation in recent years. Let me try to address your concerns and shed some light on the practicality and usefulness of AI.

Crypto Speculation vs. AI Investment: It's not uncommon for people who experienced gains or losses in one investment area, such as cryptocurrency, to look for new opportunities in other fields like AI. Some might see AI as the next big thing, leading to a surge in investments and hype around AI companies. However, AI and cryptocurrency are fundamentally different, and while there may be some overlap in investor interest, they are distinct technologies with their own set of risks and potential. AI's Practical Applications: AI has indeed shown remarkable promise in various domains. In the tech industry, AI is being applied to natural language processing, image recognition, recommendation systems, healthcare diagnostics, autonomous vehicles, and more. AI has the potential to improve efficiency, automate repetitive tasks, and enable innovative solutions to complex problems. However, it's crucial to understand that AI is not a magical solution for every problem, and its success depends on careful implementation and understanding its limitations. Generative AI: You mentioned seeing people generate bits of programming with AI. Generative AI models, like ChatGPT, can be useful for automating some programming tasks, creating code snippets, generating natural language descriptions, or even helping with creative writing. They can be valuable tools, especially for tasks that involve large amounts of repetitive text generation. AI Limitations: While AI has made impressive strides, it's essential to recognize its limitations. AI models like GPT-3 excel in pattern recognition and generating coherent text, but they lack true understanding and reasoning capabilities. They also might produce inaccurate or biased outputs if not carefully supervised or fine-tuned. Responsible Use of AI: Flashy demonstrations of AI capabilities can be attention-grabbing, but it's crucial to use AI responsibly and ethically. As with any powerful technology, there are potential risks, such as misuse or perpetuating harmful stereotypes. So, while there is genuine utility in AI, there must be a balance in understanding its capabilities and using it in ways that benefit society.

In conclusion, AI is not all hype, and it has genuine practical applications in various industries. However, it’s crucial to approach AI investment and usage with a critical eye, understanding its limitations, and using it responsibly to unlock its true potential. Like any tool, it can be valuable when applied appropriately and with clear goals in mind.