Much like automated machinery, it could in theory free the workers to do more important, valuable work and leave the menial stuff for the machine/AI. In theory this should make everyone richer as the companies can produce stuff cheaper and so more of the profits can go to worker salaries.

Unfortunately what happens is that the extra productivity doesn't go to the workers, but just let's the owners of the companies take more of the money with fewer expenses. Usually rather firing the human worker rather than giving them a more useful position.

So yea I'm not sure myself tbh

Most email spam detection and antimalware use ML. There are use cases in medicine with trying to predict whether someone has a condition early

Medical use is absolutely revolutionary. From GP's consultations to reading tests results, radios, AI is already better than humans and will be getting better and better.

Computers are exceptionally good at storing large amount of data, and with ML they are great at taking a lot of input and inferring a result from that. This is essentially diagnosing in a nutshell.

This sort of feels like someone using a PC for the first time in 1989 and asking what it does that they can't do on a piece of paper with a calculator. They may not have been far off at the time, but they would be missing the point. This is a paradigm shift that allows for a single application to fulfill the role of, eventually, infinite applications. And yes it starts with mundane tasks. You know, the kind people don't want to do themselves.

AI is a very broad topic. Unless you only want to talk about Large Language Models (like ChatGPT) or AI Image Generators (Midjourney) there are a lot of uses for AI that you seem to not be considering.

It's great for upscaling old videos: (this would fall under image generating AI since it can be used for colorizing, improving details, and adding in additional frames) so that you end up with something like: https://www.youtube.com/watch?v=hZ1OgQL9_Cw

It's useful for scanning an image for text and being able to copy it out (OCR).

It's excellent if you're deaf, or sitting in a lobby with a muted live broadcast and want to see what is being said with closed captions (Speech to Text).

Flying your own drone with object detection/avoidance.

There's a lot more, but basically, it's great at taking mundane tasks where you're stuck doing the same (or similar) thing over, and over, and over again, and automating it.

They are the greatest gift to solo-brainstorming that I've ever encountered.

_ /\ _

Anything that requires tons of iteration can be done way faster with AI. Finding new chemical formulas for medicine, as an example. It takes a "throw everything at the wall and see what sticks" approach, but it's still more effective than a human.

AI has some interesting use cases, but should not be trusted 100%.

Like github copilot ( or any "code copilot"):

• Good for repeating stuff but with minor changes
• Can help with common easy coding errors

• Code quality can take a big hit
• For coding beginners, it can lead to a deficit of real understanding of your code
  ( and because of that could lead to bugs, security backdoors.... )

Like translations ( code or language ):

• Good translation of the common/big languages ( english, german...)
• Can extend a brief summary to a big wall of text ( and back )

• If wrong translated it can lead to that someone else understands it wrong and it misses the point
• It removes the "human" part. It can be most of the time depending on the context easily identified.

Like classification of text/Images for moderation:

• Help for identify bad faith text / images

• False Positives can be annoying to deal with.

But dont do anything that is IMPORTANT with AI, only use it for fun or if you know if the code/text the AI wrote is correct!

An interesting point that I saw about a trail on one of the small, London Tube stations:

• most of the features involved a human who could come and assist or review the footage. The AI being able to flag wheelchair users was good because the station doesn't have wheelchair access with assistance.

• when they tried to make a heuristic for automatically flagging aggressing people, they found that people with the arms up tend to be aggressive. This flagging system led to the unexpected feature that if a Transport For London (TFL) staff member needed assistance (i.e. if medical assistance was necessary, or if someone was being aggressive towards them, the TFL staff member could put their arms up to bring the attention onto them.

That last one especially seems neat. It seems like the kind of use case where AI has the most power when it's used as a tool to augment human systems, rather than taking humans out of stuff.

It's sped up my retouching workflows. I can automate things that a few years ago would've needed quite a lot of time spent with manual brush work.

Also in the creative industries, it's a massive time saver for conceptual work. Think storyboarding and scamping, first stage visuals that kind of thing.

AI is a revolution in learning.

Our software uses ML to detect tax fraud and since tax offices are usually understaffed they can now go after more cases. So yes?

One of the better uses I’ve heard of is in search and rescue type situations. Using AI to find specific items, people or anomalies on a map or video feed can be helpful.

An example regarding wildfires:

California turns to AI to help spot wildfires

Lots of boring applications that are beneficial in focused use cases.

Computer vision is great for optical character recognition, think scanning documents to digitize them, depositing checks from your phone, etc. Also some good computer vision use cases for scanning plants to see what they are, facial recognition for labeling the photos in your phone etc…

Also some decent opportunities in medical research with protein analysis for development of medicine, and (again) computer vision to detect cancerous cells, read X-rays and MRIs.

Today all the hype is about generative AI with content creation which is enabled with Transformer technology, but it’s basically just version 2 (or maybe more) of Recurrent Neural Networks, or RNNs. Back in 2015 I remember this essay, The Unreasonable Effectiveness of RNNs being just as novel and exciting as ChatGPT.

We’re still burdened with this comment from the first paragraph, though.

Within a few dozen minutes of training my first baby model (with rather arbitrarily-chosen hyperparameters) started to generate very nice looking descriptions of images that were on the edge of making sense.

This will likely be a very difficult chasm to cross, because there is a lot more to human knowledge than thinking of the next letter in a word or the next word in a sentence. We have knowledge domains where, as an individual we may be brilliant, and others where we may be ignorant. Generative AI is trying to become a genius in all areas at once, and finds itself borrowing “knowledge” from Shakespearean literature to answer questions about modern philosophy because the order of the words in the sentences is roughly similar given a noun it used 200 words ago.

Enter Tiny Language Models. Using the technology from large language models, but hyper focused to write children’s stories appears to have progress with specialization, and could allow generative AI to stay focused and stop sounding incoherent when the details matter.

This is relatively full circle in my opinion, RNNs were designed to solve one problem well, then they unexpectedly generalized well, and the hunt was on for the premier generalized model. That hunt advanced the technology by enormous amounts, and now that technology is being used in Tiny Models, which is again looking to solve specific use cases extraordinarily well.

Still very TBD to see what use cases can be identified that add value, but recent advancements to seem ripe to transition gen AI from a novelty to something truly game changing.

Don't limit your thoughts to just generative AI, which is what you are talking about. Chat bot and media generation aren't the only uses for AI (by which I mean any trained neural network program that can do some sort of task.

Motor skills

AI can solve learn to solve the marble maze "Labyrinth" much, much faster than a human, and then speedrun it faster than any human ever has. Six hours. That's how long it took a brand new baby AI to beat the human world record. A human that has been learning hand-eye coordination and fine motor control all of it's life, with a brain which evolved over millions of years to do exactly that.

No special code needed. The AI didn't need to be told how balls roll or knobs turn, or how walls block the ball. It earned all of that on the fly. The only special code it had was optical and mechanical. It knew it had "hands" in the form of two motors, and it knew how to use them. It also had eyes (a camera), and access to a neural network computer vision system. When the AI started taking illegal shortcuts, and they had to instruct it to follow the prescribed path, which is printed on the maze.

Robots could in work factories, mines, and other dangerous, dehumanizing jobs. Why do we want workers to behave like robots at a factory job? Replace them with actual robots and let them perform a human job like customer service.

Think of a robot that has actual hands and arms, feet and legs, and various "muscles". We have it learn it's motor control using a very accurate physics system on a computer that simulates its body. This allows the AI to learn at much faster speeds than by controlling a real robot. We can simulate thousands of robots in parallel and run the simulations much faster than real time. Train it to learn how to use it's limbs and eyes to climb over obstacles, open doors and detain or kill people. We could replace police with them. Super agile robot cops with no racial bias or other prejudices. Arresting people and recording their crimes. Genuine benefit.

Computer Vision

AI can be trained to recognize objects, abstract shapes, people's individual faces, emotions, people's individual body shape, mannerisms, and gait. There are many genuine benefits to such systems. We can monitor every public location with cameras and an AI employing these tools. This would help you find lost loved ones, keep track of your kids as they navigate the city, and track criminal activity.

By recording all of this data, tagged with individual names, we can spontaneously view the public history of any person in the world for law enforcement purposes. Imagine we identify a person as a threat to public safety 10 years from now. We'd have 10 years of data showing everyone they've ever associated with and where they went. Then we could weed out entire networks of crime at once by finding patterns among the people they've associated with.

AI can even predict near future crime from an individual's recent location history, employment history, etc. Imagine a person is fired from his job then visits a gun store then his previous place of employment. Pretty obvious what's going on, right? But what if it happens over the period of two weeks? Difficult for a human to detect a pattern like this in all the noise of millions of people doing their everyday tasks, but easy for an AI. Genuine benefit.

Managing Production

With enough data and processing power, we can manage the entire economy without the need for capitalism. People's needs could be calculated by an AI and production can be planned years ahead of time to optimize inputs and outputs. The economy--as it stands today--is a distributed network of human brains and various computers. AI can eliminate the need for the humans, which is good because humans are greedy and neurotic. AI can do the same job without either. Again, human's are freed to pursue human endeavors instead of worrying about making sure each farm and factory has the resources it needs to feed and clothe everyone. Genuine benefit.

Togetherness

We will all be part of the same machine working in harmony instead of fighting over how to allocate resources. Genuine benefit!

I use it daily to generate basic Perl scripts that I cant be bothered to write myself. It’s fantastic.

Someone I know recently published in Nature Communications an enormous study where they used machine learning to pattern match peptides that are clinically significant/bioactive (don’t forget, the vast amount of peptides are currently believed to be degradation products).

Using mass spectrometry, they effectively shoot a sawed off shotgun at a wall then using machine learning to detect pellets that may have interesting effects. This opens up for new understanding in the role peptides play in the translational game as well as a potential for a huge amount of new treatments for a vast swathe of diseases.

Machine learning is important in healthcare and it's going to get better and better. If you train an algorithm on two sets of data where one is a collection of normal scans and the other from patients with an abnormality, it's often more accurate than a medical professional in sorting new scans.

As for the fancy chatbot side of things, I suspect it's only going to lead to a bunch of middle management dickheads believing they can lay off staff until the inevitable happens and it blows up in their faces.

Maybe you only do an "odd bit" of mundane writing and the image/music generation is a gimmick, but a lot of the modern world is mundane and pays people lots of money for mundane work. E.g. think of those internal corporate videos which require a script, stock photography and footage, basic corporate music following a 4 chord progression, a voiceover, all edited into a video.

Steve Taylor is most famous for being the voiceover for Kurzgesagt videos, but more generally he's a voiceover artist that features in lot of these boring corporate videos. This type of content has such high demand there is an entire industry dedicated towards it, which seems well suited to AI.

https://youtu.be/vDb2h1-7LA0

This does raise further ethical/economical issues though, as most people in these creative industries actually require income from this boring work to get by.

There are lots of things that are very hard to program, but people can do very easily. For example, play Go or recognize that an animal is a bird.

Machine learning/ai makes it competitively simple to make computers do some of these things, but at the cost of efficiency and speed at runtime. This is true if computers vs people as well, a human brain is much slower, less efficient, and less accurate than a calculator.

Machine learning/AI is exciting because it enables computers to quickly be trained to do tasks that were impossible or would have required years of dedicated effort. The tech world is excited about it because whole new enterprises and areas of tech may spring up, big markets that were previously out of reach.

Downsides:

• AI uses a lot more electricity. Especially for things that computers can already do, using AI is very inefficient.

• Limited control. You train an ai model to do a task, but you don't have direct control over how it thinks. If chatgpt gives a wrong answer, they can't just trace the program and figure out why. It takes serious effort to figure out how chatgpt answers simple questions, so figuring out how it gets complex answers or why an answer is wrong is nearly impossible at this point. This also applies to unwanted behaviors,if you had a really good history chatbot who happened to turn out racist, you can't just turn that off. You end up having to retrain the model, or secretly add "make sure your answer isn't racist" to every submitted prompt.

My partner and I have founded a company that uses custom AI models trained on research to (partially) automate the process of peer review and replication. We can identify mistakes and some types of fraud in research to aid reviewers as well as extract methods and equations from papers and automatically verify findings. If you know anything about the state of research right now, those are some incredibly large benefits.

The legal industry is going to get turned on its head when AI can read, comment, and write contracts.

I pasted your question verbatim into Bing Chat. Here's what it responded with:

Artificial Intelligence (AI) indeed has a wide range of benefits that extend beyond the ones you’ve mentioned. Here are some areas where AI is making a significant impact:

• Healthcare: AI is used in predicting disease outbreaks, drug discovery, personalized treatment plans, and improving patient care. For example, machine learning models can analyze medical images to detect diseases at early stages.
• Education: AI can provide personalized learning experiences, identify gaps in learning materials, and automate administrative tasks. It can adapt to individual learning styles, making education more accessible.
• Environment: AI can help in climate modeling, predicting natural disasters, and monitoring wildlife. It’s also used in optimizing energy usage in buildings and manufacturing processes, contributing to sustainability.
• Transportation: Autonomous vehicles use AI for navigation, safety, and traffic management. AI can also optimize logistics, leading to reduced costs and environmental impact.
• Security: AI can enhance cybersecurity by detecting unusual patterns or anomalies in data, helping to prevent cyber attacks. It’s also used in surveillance systems to identify potential threats.
• Accessibility: AI can help people with disabilities by providing tools that improve their ability to interact with the world. Examples include speech recognition for those unable to use a keyboard, and visual recognition systems that can describe the environment to visually impaired individuals.

While it’s true that AI can be used to generate profits for corporations, it’s important to remember that many of these advancements also lead to societal benefits. However, like any technology, AI can be misused, and it’s crucial to have regulations and ethical guidelines in place to prevent such misuse. The creation of “bots and fake content” you mentioned is one such misuse, and efforts are ongoing to combat these issues.

In conclusion, AI has the potential to greatly benefit society in many ways, but it’s equally important to be aware of and address its challenges.

Seems like a pretty comprehensive list of the things I'm aware of myself. There's also tons of interesting future applications being worked on that, if they pan out, will be hugely beneficial in all sorts of ways. From what I've seen of what the tech is capable of we're looking at a revolution here.

The one thing I can say for sure is that, sometimes, when I library or something has bad documentation it might be able to give a solution quicker than diving I to the source code

I would've found it extremely useful in school for studying advanced topics in biology, and now I use it to explain programming concepts to me, or to explain other languages. Some of the answers really do feel like you have a world-class tutor right next to you. It's not without errors but it's mostly accurate and insightful.

It's also really good at helping you search for things that you can't just type into a search box using keywords. Like, you can give it a general description of what you're thinking about and it'll guess. I've used it for TV shows from the 90-00s I largely forgot about, but also words, phrases, or concepts I can't quite remember. One time I was trying to remember a famous experiment but gave it the wrong scientist and it correctly guessed who it was and what the experiment was about.

It's also useful for brainstorming. You give it a general description of what you're doing and it'll give you somewhat generic recommendations of what you could expect other people to do so that you cover most bases. I've also used this for discussions where I'm not sure about my position so I'll ask it to get a better idea about the problem and to figure out what I'm not considering.

Overall, I think it's a great general purpose assistant.

something I'm not seeing here is business applications in supply chain. Managing forward-stocking warehouses, monitoring shipping lanes and ordering for seasonality, as well as identifying anomalies such as chargebacks, stock outs, outlier returns/damages/failures is typically managed by a handful of people mixing spreadsheets, ERP databases, and emailing people to tell them "your light bulbs are stuck in the suez canal and your recent batch of cables have a defect"

AI can replace these systems with ML, and use LLMs to generate the notifications.

If by AI you mean current language learning models then it looks like it can do some useful stuff and is worrying how close it is to doing amazing things.

If by AI you mean a more general concept of artificial intelligence then yeah. Intelligence iis one of the most important resources for getting what we want. This is not to say there are not valid concerns with AI but the potential is crazy, like humans not needing to work levels.

It's massively important in the sciences, both for computing purposes and theoretical design and investigation purposes.

AI is completely revolutionizing genetics research and subjects like biochemistry and pharmacology, because it's able to extrapolate from already identified genes and compounds and find new ones or identify the purposes of genes just from their sequence structure.

It's made processes that would take weeks or months just to identify a single new component to something that takes days or hours.

Once the technology has embedded, our societal adjustments have completed (and they will be PAINFUL) and assuming the profit of AI is sufficiently taxed for the wealth to redistribute, AI will be seen as the Industrial Revolution x10.

Most likely however, the rich will get richer.

Depends on what kind of AI. In gaming, AI is part of the process to entertain and challenge the player, and has even been used to help model life systems.

I have yet to see how useful LLMs can be outside of being blatant plagarists but for a time, projects like AI Dungeon really did push the emphasis on "interactive dynamic narratives" and it was really fun for a while.

ML has been an important part in fraud detection for at least a decade now.

I think as a tool to synthesize and collect and organize information to help people make decisions, it has potential. Much like how machine learning is used to look at a bunch of MRI scans and highlight abnormalities and then medical professional looks at those anomalies to decide if they might be a tumor. But a machine is really good at finding things that are anomalous enough to be worth looking at. 

Things that you might have delegated to a secretary or assistant or business analyst might be worthwhile done by an LLM. “sort all these papers by which ones understood the topic the best so I can read those first“ “Do any of these articles contain new information I haven’t seen before?“ “based on the Billboard top 20, create 5 catchy beats for a backing track” “Draft a letter to this customer apologizing for our error and offering them a coupon for their next order” “analyze this email I wrote and help me make the tone more professional” 

I am terrified by what is going to be possible with phishing scams, spam email, fake articles, deep fake videos, reproduction of copyrighted works, an overwhelming volume of trademarks and patents that are meaningless, obtuse contracts that are purposely difficult for a human to read but contain surreptitious loopholes, software that is full of flaws and back doors, and corporations putting more barriers between customers and customer service people.

“find me the 50 most popular articles on this topic, synthesize them all into a 20 bullet point summary and highlight for me the differences of opinion presented so I can understand both sides of the issue” - super useful

“Generate 100,000 unique variations on a very professional email correspondence from a Nigerian Prince offering to pay $50,000 transaction fee for assistance with an international wire transfer “ - no

Unfortunately I don’t think there are any incentives for the companies building these things to limit use or install the guard rails necessary. And our laws, which always run a little behind technology, are thoroughly outpaced by the rate of innovation here. The very old people in charge of governments have no chance of staying ahead of these companies. It will get much worse before it ever gets better.

Honestly, we should just stick to porn. The Internet should just be for porn because everything else we do with it seems to turn evil. 🫤

Have you tried out writing prompts for an image generating AI? If you have some idea and play around with it it's quite a new thing. And extension of human imagination. YMMV

AI is helping us to correctly predict protein folding which will enable new medication. Afaik it's a major breakthough that could allow alleviating a lot of suffering.

Lots of it's actual AI. Nothing we have at the moment I would actually qualify as true AI. It's just algorithms spitting out and answers what it interprets your question as. They don't think or create anything, just regurgitate things in predefined patterns.

No one knows the long term benefits/costs yet, but its potentially more empowering to small creators than large ones. Everyone has access to the same tools, and for instance, if it can offload a bunch of work from an indy game dev, that could let them focus more on the part of the game design process they are most skilled at/interested in.

Permanently Deleted

It's great for duping stupid people. There are no ethical benefits to the current LLM AI on the market.

It's got potential for use in research such as identifying potential medications to work with certain diseases based on molecular structure, something that would take a normal human countless hours but a machine could do in seconds, but AFAIK that field is a very tiny fraction of the market.

Not for you or I.