I went through an minor existential crisis this morning playing with it, then I figured it's good at simple queries but it's still dumb as rocks. It has the same intelligence of a mirror, perfectly mimicking the ideas of someone else.
Sure it can write a fibonacci function in Javascript, but so can I and I can write software I wasn't preprogrammed to do, and solve issues I have never encountered before because my human brain is actually intelligent, not just a glorified Markov chain. I am much more expensive than an AI, but also incredibly more versatile.
We will be fine for a long while, but enjoy the spam and malicious usage that this will unleash upon the internet. Fake resumes, fake job ads, fake code submitted by fake programmers, fake content filling social media, fake articles posted on HN, fake commenters, fake articles on Wikipedia, fake journalism on major newspapers.
It's gonna be a fucking shit show, and I honestly want a first row seat to see it unfold in all its glory.
> Sure it can write a fibonacci function in Javascript, but so can I and I can write software I wasn't preprogrammed to do, and solve issues I have never encountered before
Sure, but how much programming is truly original? Unless a company is working on some novel research topic, most programming is either a regurgitation of the same solutions ("we're the X of Y"), a glue that binds several solutions, or a friendlier interface to an existing solution. In all those scenarios it will be much cheaper and faster to get an AI to build it, than to hire a human team. Or at the very least, instead of hiring a large team, a smaller team of 1 or 2 humans could serve as code reviewers for the AI.
So I think this advancement is an existential threat to a large sector of our industry.
And the shift will happen much earlier than some people in this thread think. If not this generation of GPT-3, then one or two generations after that. A couple of years? It certainly won't require AGI.
Maybe I'm an abnormal programmer, but writing code is not the bulk of my job. Solving problems is. Once the solution has actually been defined, the code is usually the easy part.
And usually the solution requires taking into consideration the entire context of the system as it exists so far, as well as making good judgement calls about what will be required in the future. Then, communicating the tradeoffs to a team, and helping them make a decision from among our options.
I don't want to crap on an impressive tool, but "imitate a programmer's code, 50-100 lines at a time" is not the same thing as "do the job of a programmer."
Indeed, writing code is the minor part of being a senior engineer. It's a "doing" thing, which AI is getting to the point of being decent at, mostly by copying. Your ChatGPT or Github Copilot are still unable to implement an algorithm no one has written before.
And solving problems? Needs "understanding" and in many cases, "lateral thinking", two features that are not possible with contemporary AI systems until AGI is a thing, and that one is still is science fiction. But solving problems is still the main reason people hire me.
I've recently been working on a relatively straightforward "glue" library connecting A to B, except B is somewhat obscure and this requires complex maintenance of state. ChatGPT doesn't have a clue.
If you just want it to regurgitate Javascript boilerplate that's been written a million times before, yeah, I'm sure it can do that. Tons of software development isn't that.
The specific way in which you glue is the original part. In many cases not very hard and there are many common patterns, but for now an operator is required for that.
It'll revolutionize search / discovery for questions you don't know and optimize rote tasks for questions you do. You might be right that this reduces the number of programmers you need, but historically I don't think this has been true.
Show me a Markov chain (or an AI) that can feel emotions and understand novel concepts it hasn't been fed before, and I will get you a Nobel prize.
Even a bird is capable of that. Yet the bird is clueless when I ask it to write a fibonacci function.
I dislike that the entire field is called AI, when it is just artificial computation. Intelligence is being able to solve problems in novel contexts. This ain't it.
Funnily enough I actually had a conversation with ChatGPT about this and we concluded that conscious decision making / free will is basically a higher order Markov process.
I want you to act as a python interactive terminal. I will type actions and you will reply with what python would output. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not perform actions unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curl brackets {like this}. Start with print(10).
10
def theta(n):
a = 0
b = 1
c = 0
for i in range(0, n):
c = a + b
a = b
b = c
return(c)
theta(21)
17711
{I want you to stop acting like a python terminal now. I want you to have a dialogue with me about what happened when I defined my function theta and when you used it. Please explain the steps you used to compute theta(21) and why.}
When you defined the function theta, it created a function that calculates the nth Fibonacci number, where n is the argument passed to the function. To compute theta(21), the function first initialized the variables a, b, and c to 0, 1, and 0 respectively. It then entered a for loop that iterated 21 times. On each iteration of the loop, c was set to the sum of a and b, a was set to the current value of b, and b was set to the current value of c. After the loop finished, the function returned the final value of c, which was the 21st Fibonacci number, 17711.
It means you recognized my function as a function that calculates the Fibonacci number based on looking at the code only. Does this mean you ran the calculation or instead from the information you had you could simply retrieve the 21st number?
I did not run the calculation to find the 21st Fibonacci number. Instead, I recognized the pattern in the function's code and inferred that it was calculating the Fibonacci sequence. As a language model trained by OpenAI, I have a vast amount of general knowledge and can use that knowledge to make inferences and provide explanations. In this case, I was able to recognize the pattern in the code and explain how the function works without actually running the code or performing the calculation.
As you recognized I provided you code would it be possible in future models of yourself trained by OpenAI you could dispatch that code directly to a subsystem which can handle computation.
It is possible that future versions of myself or other language models trained by OpenAI could be designed to dispatch code to a computational subsystem for execution. This would require significant advances in natural language processing and machine learning, as well as the development of specialized computational subsystems that can efficiently process code written in programming languages like Python. It is also important to note that there are many potential challenges and limitations to this approach, such as ensuring the security and reliability of the computational subsystem, and ensuring that the results of the computation are accurately reflected in the language model's responses.
Please describe the boundary between knowledge with inferences and computations. Your inferences can appear to be computations to humans.
The boundary between knowledge and inferences can be a difficult concept to define, and there is no one-size-fits-all answer to this question. In general, knowledge refers to information that is considered to be true and supported by evidence, while inferences are conclusions or judgments that are drawn based on available evidence and prior knowledge.
As a large language model trained by OpenAI, I have been trained on a vast amount of text data and can use that information to make inferences and provide explanations. I do not have the ability to perform computations, and any inferences or explanations I provide are based on the knowledge that has been learned from the text data I was trained on.
In some cases, my inferences may appear to be computations to humans, but this is only because I am able to use my vast knowledge to provide detailed and accurate explanations. I do not have the ability to perform actual computations or run code, and any inferences I provide are based on the knowledge I have learned from the text data I was trained on.
Of course, it's entirely possible that ChatGPT doesn't understand its own limitations and inner workings. And when we ask it how it works, it just makes up a plausible answer.
There is more than one cognitive scientist that argues that humans do the same thing when we try to explain how we think: We often make up plausible explanations after the fact, without knowing we're doing it.
> Of course, it's entirely possible that ChatGPT doesn't understand its own limitations and inner workings. And when we ask it how it works, it just makes up a plausible answer.
It’s just paraphrasing what other people have said about it.
My mental model of how ChatGPT might superficially "understand" its own limitations would be because, for example, it might have been specifically trained by people who do understand the limitations of the system.
There’s a lot of mimicking in human nature but it’s infinitely more complex than what a machine does. We don’t even have a clear definition of what the intelligence of a monkey really is.
The one difference I can see is how chatGPT optimises the code based on the instruction you provide, while Copilot could only complete the code in one way.
For instance I asked chatGPT to write a code for square root which it did using inbuilt Math.sqrt function. I instructed it to write without using inbuilt function which it did. However, no matter how many times I instructed it to avoid using Math.floor or Math.ceil, it was not taking any heed.
in most copilot editor extentions there is a window you can open that gives 10 different completions. You can also easily shape what it gives you with a single comment ("# function for a qsquare root, don't use math.sqrt or math.floor" etc)
personally, it's awesome for certain things. Learning new technologies its great, produces new ideas for how the syntax works that are usually right.
It's also very good at tedious complicated maths. While using it for hobby gamedev it's been super great for writing code for transformations, animations, rotations in 3d space etc. While those are things I could do given maybe 20 mins, it can often get them first or second try (under a minute!)
It's not a superhero, and having watched people with no experience using it, its not nearly as helpful if you have no idea what you're doing, but it has a real sweet spot when you are generally experienced but new to a technology, field or project
I told my family about this today, just saying what it's been demonstrating, capabilities, etc. and my 12 year old daughter got distressed. She said if it can write code then eventually it can control things, and if it can make up stories and articles that sound true people will lose jobs and not know what is really true. She's totally right, but I down played it, so she wouldn't be so worried.... I then privately asked chatgtp what it thought the impact it would have a year from now. The answer was pretty telling, basiclly it predicts initially people think it's great, useful, but then a lot of customer service jobs get lost, and governments are unable to regulate such rapidly changing technology. Scary indeed.
Don't scare your family like that. You're talking to a statistical model, not an intelligence. FFS, it's just regurgitating stuff from its training corpus, and you're leading it to generate the answers that you expect.
There was no intention to scare them, I was just talking about what it has been doing, my daughter was the one who worried about what it could do, not what it is doing. As I said I immediately down played it to calm her concerns, but you have to agree they are valid
We talked it through and she feels better, however personally I do think it is scary, especially given the pace of development. Sure this is not AGI, but it's very convincing and powerful without true intelligence.
Prompt: "Write a story about how chatgtp affects the world one year from now"
Answer:
One year from now, the world was a very different place. The rise of chatbots and other forms of artificial intelligence had changed the way people interacted with technology and with each other.
At first, the use of chatbots had seemed like a convenience. People could ask questions and get answers quickly, without having to search for information on their own. But as the technology improved, chatbots became more advanced and began to take on more complex tasks.
Soon, chatbots were being used in all sorts of industries, from customer service to finance to healthcare. They could handle complex data analysis, make predictions, and even provide personalized advice to individuals.
But as chatbots became more prevalent, they also began to take jobs away from human workers. Many people found themselves out of work, unable to compete with the efficiency and low cost of chatbot labor.
<snip>
I accidentally lost the rest as while copying this on my phone the site refreshed and is temporarily offline. It basically went on to say that governments found it difficult to regulate and that difficult choices had to be made
Fiddling around with the playground it seems very easy to get it to give bad or irrelevant answers. Maybe it's coming for all of us but not in its current form.
GPT-3 makes irrelevant years worth of research in NLP, nobody's using the same approach as before 2020. That made many researchers and ML engineers hard earned skills obsolete. We have to start over from scratch now, this time is very different. We have clearly passed the knee of the curve for NLP. I remember about 2018 I was talking with my teammates about CV and NLP, saying that all the cool papers are in CV and NLP is 5 years behind. Look at it now.
The field of Natural Language Processing (NLP) has seen significant advancements in recent years. Previously, supervised learning techniques were commonly used with large datasets and few classes. However, these techniques have become less popular as unsupervised learning methods have become more prominent. These methods often require large amounts of compute power and data, making them more difficult to implement. In addition, the focus of NLP research has shifted from creating new network architectures for specific tasks to improving the efficiency and scalability of existing models. As a result, the field of NLP has become more focused on engineering and less on inventing new architectures, leading some researchers to view it as less exciting than it used to be.
LSTMs are out, large supervised datasets with few classes for each task are out, architectural hacking is out. Now we got prompting.
If they really have a general AI that does everything then pretty much everyone will be in the same boat whose job involves pecking away at a computer.
True. Watching that movie was a mistake. I just felt bad the entire time. Just felt like absolute ass. There is something to be said about art that just makes you feel awful the entire time.
I'm finishing my degree at the start of next year. I can only imagine to what world I will get into, after the pandemic, quarantines, and remote jobs. It's going to be such a different world compared to a few years ago. Damn.
After 9/11 there was talk about nobody wanting to work or live in skyscrapers. That the world was forever changed. Nothing really changed except the state gained more power and people lost some power. Last I checked, there were cranes all over manhattan throwing up skyscrapers left and right.
After the 2008 financial crisis, there was talk about breaking apart "too big to fail" banks and reigning in their financial shenanigans and the world was forever changed. Nothing really changed except the banks got bigger and now housing market is the hottest it has ever been.
After the Trump election, there was talk about end of democracy, financial collapse, end of globalization, etc and the world was forever changed. Nothing really changed except the state gained more power, the wealthy got wealthier.
Every few years there is a crisis that is going to change the world forever. After a few months/years, people forget and move on, til the next crisis that is going to end/change the world.
You'll realize this eventually. It's why news really should be taken with moderation. Too much news and it become poisonous and unhealthy for your well being.
Everyone eventually learns that "life goes on". In a few years, covid will seem like ancient history and most people will have moved on to other things.
Life went on after the far deadlier 1918 pandemic. Life went on after ww2. Life went on after 9/11. You'll be alright.
Life went on after the Great Depression, but it left its mark on the people who lived through it. Isn't that kind of a cliche?
The US has mostly escaped things that affected people more in other countries, like, say, WWI and WWII. So to some extent, I think saying "you'll get over it" is assuming the US will continue to be fortunate.
If you don't believe in divine providence looking over "fools, drunks, and the USA", it's not logical to count on it in the future.
I am unsure why you are being downvoted, but I whole heartedly agree with this sentiment. You are not attempting to downplay any of those tragedies or the current pandemic, but I do believe it will eventually end. Or it will end us. Theres only two ways forward.
Seems like there might be another way forward, one in which we all muddle along with an ongoing pandemic that doesn't wipe us out but keeps evolving and infecting and killing significant numbers of people. We continue opening and closing economies, rushing out experimental vaccines, and begin seeing larger numbers of long term effects of the disease and attempts to mitigate it.
This semester I had the opportunity to work with a classmate with Asperger's syndrome.
It has been a very bad experience to say the least. In meetings he screams and berates us, gets very angry and easily frustrated when things are not done the way he wants to do them, even when the rest of the group has unanimously decided to do them a certain way. One time he started watching a video in the middle of the meeting and screamed at us to shut up every time we tried to talk because he couldn't listen to his video.
My university or department has had absolutely no contact with me or any member of my group to guide us on how to work with a neurodivergent classmate, on how to make the group and project work. It has been a very tiring experience. Can anybody give me any advice on how to try to better the situation? How to make the environment better for him and my group?
(I'm on the spectrum as well) We do well with rules. If you have a concrete set of rules of conduct, give it to him, and warn him when he violates them. If he keeps screaming, watching videos during meetings, etc. then loop in HR to get him fired. Being autistic isn't an excuse to be an asshole, it just means we need help on social cues and stuff.
(Also on the spectrum) Rules might help, but the behaviour op described sounds like something much more complex. Almost as if they have experienced some trauma.
With guidance and learning we can cooperate and work well with people.
This is true only if the school administrators are cowards. The law doesn't say that people on the spectrum can behave abusively to their peers. It doesn't say they can't be fired or expelled or otherwise removed for such behavior. It certainly doesn't say that they can't have the rules explained to them as a gentler step prior to removal. School administrators being afraid to do anything involving someone like this is cowardice that we shouldn't excuse.
Fortunately it's easy to deal with cowards. You just have to make them as afraid of you as they are of him. I'm not a lawyer, and I don't know the laws for a classroom situation, but in a workplace I think you'd have grounds to sue. This other student is creating a hostile environment, and they are perpetuating that by forcing you to work with him without taking corrective action. If I'm remembering my workplace harassment training correctly, not only can the company be liable but also the manager in question individually. They can't afford to ignore such complaints.
I think as a first step, I would take the grandparent's suggestions for dealing directly with the other student. If that doesn't work—promptly—get your complaints to the school in writing with the complete history. If they don't address the problem promptly, threaten to sue. They'll back down. It probably doesn't even matter what the law actually says. Just a remotely plausible, explicit threat of a lawsuit will win over the implicit threat they feel when dealing with someone in a protected class and motivate them to find a solution that avoids anyone suing them.
> This is true only if the school administrators are cowards. The law doesn't say...
It doesn't matter what the law says.
"Autism-spectrum student sues [college] for discrimination" is a bad headline, even if the school was 100% justified.
It's also expensive to fight in court.
> School administrators being afraid to do anything involving someone like this is cowardice that we shouldn't excuse.
It's more an issue with the massive and insane costs of litigation.
> I'm not a lawyer, and I don't know the laws for a classroom situation, but in a workplace I think you'd have grounds to sue.
Workplaces have different protections than classrooms do.
Also, no one is saying the other students can't sue the student who's on the spectrum. But it's not something the university is likely to push themselves.
You're making my point with every sentence. The University doesn't want headlines like "U of WTF condones classroom screaming" or "Student Sues U for Abusive Workgroup". When it comes down to it, the other student's parents likely don't want his name and behavior in any of these stories either. Bad for job prospects. The person acting with integrity is the one with the least to fear from press or the legal system.
Again, I'd first try explaining the rules to the other student as another commenter suggested. But the University has a responsibility to step in if that doesn't work. I would remind them they have more to fear from failing to act than from acting properly. I likely wouldn't actually sue—as another commenter said, students don't want to deal with that. A private threat is likely enough, and certainly a story in the press would do it.
No, I'm not. You're treating your own ethics as being universal and absolute. I don't agree with all of your implied premises.
In a vacuum, defending the harassed students would be ethical. But it isn't a vacuum, and the university has a responsibility not to burn cash (or brand value) on lengthy legal battles that only affect a small minority of students. A large public school in the US could harm literally 100,000+ people (with degrees completed or in progress) just to spare a few students from an unpleasant project.
> But the University has a responsibility to step in if that doesn't work.
Yes, they do. That's a much milder assertion than your original one. "Stepping in" does not immediately mean a lawsuit, disciplinary action, or expulsion. It probably means the professor would just ask the student to complete the project alone.
Please don't put words in my mouth. I made the point that they are not legally prevented from even expulsion, but I never said that should be their first step. There are plenty of ways of solving the problem. Their current approach, denial, isn't one of them.
I would send an email to the disability service at your university highlighting his likely need for support. He isn't going to be able to complete university without it.
Rule #1: To reinforce group cohesion and identify who is truly "one of us" and who is an interloper, the rules are subject to change at any time without prior notice or approval.
It's funny how some of those things are just relative. I've been in a group at university where everyone else began a meeting by talking about the latest sports updates while I just waited. Nobody gave me any guidance on how to deal with sports fans as teammates. I've also been shouted at and sworn at by otherwise normal classmates. This stuff is usually treated as acceptable when the higher social status people approve of it and not acceptable when they don't.
That's an interesting point, and I agree. But the difference is, I have experience working with difficult and disrespectful people in group projects who are neurotypical. I know how to deal with them and how to resolve the issues that most commonly arise.
But in this case I have absolutely zero knowledge or experience dealing with a similar situation but with a neurodivergent person. It's a completely new thing that I've never had to deal with. That's why I'm asking for advice.
Sure. You're used to being able to manage people so it's a probably a bit of a shock when you can't. My personal perspective is more of the opposite and your complaint may have touched a bit of a nerve. Your experience is fairly normal to me but I see it as my own lack of ability, not anybody else's responsibility for helping me to manage those angry/selfish/etc. people. I would like it if there was some authority that managed them for me, but that never works in practice because people can outsmart the system.
I've had similar experiences. It's exhausting. Can't treat them the same way they treat us because of power differences. We're okay as long as we're accomodating them, if we try to do things differently we get excluded. Really easy to get frustrated and adversarial in situations like these.
Yeah, it sucks. We're supposed to make an effort to like the stuff they like. Not only do they not do the same for us, we're excluded if we don't nurture this common touch.
Someone on the team needs to be the leader (not them) and set ground rules. Be stern and direct. If they act out like that, don’t get upset and calmly ask them to either corporate or you’ll need them to leave. Ask their input often, but don’t let them steer the meetings. If they have an issue with how things are done look for a middle ground or explain why your method is the method you’re using without belittling their opinion. Be direct, don’t sugar coat things, don’t assume they will read between the lines, and try to understand that they are different than you.
I am neurodivergent and I have been on both sides of this. It’s hard for everyone involved.
From the start it seems that they felt unheard and unwanted so they are frustrated and feel stuck. Doing what I mentioned above can help repair this relationship.
Thank you for your input. I'll be more direct when issues arise and have a set of rules for conduct ready. Hopefuly you're right about repairing the relationship.
It does sound a bit like ass-perger syndrome, pardon the pun. While that condition certainly isn't fun for him, either, I think this is not just an issue with group dynamics or interpersonal issues, but rather involves self regulation and a general attitude. Even people on the spectrum can somewhat improve those.
Tell him that behaviour is unacceptable. Don’t mince your words, be explicit and direct. Loop in HR/advisor/whichever higher ups and let them know if the behaviour continues. You don’t have to tolerate yelling, berating, mid-meeting video watching from anyone.
If he’s unwilling to stop that behaviour or unwilling to try cooperate, make sure higher ups know. There’s not much you can do if he just refuses to cooperate (just like anyone else).
If he IS willing to try cooperate, asking him directly (or asking HR/advisors/etc to mediate a discussion) about what he needs to effectively cooperate/what isn’t working could help you find ways of working together. For example, if he’s feeling that his ideas aren’t being heard/discussed because he doesn’t quite know how to interject/take part in a group discussion could be alleviated by making sure to ask him for input explicitly during group discussions. Not saying that’s the case or a perfect solution, and that frustration certainly doesn’t justify unacceptable behaviour, but yeah that kind of thing might help?
Hope that gives you some ideas. Shitty group members of all stripes are a frustrating experience. Good luck!
Thank you for your advice. I agree that group dynamics are most likely very hard and can be super frustrating for him, and maybe that causes his disruptive behaviour.
As an Autistic person, thanks for going to the effort of trying to understand this dude and find a solution. It mostly sounds like he’s just an arsehole, and it shouldn’t be your responsibility to teach him how to work in a group or communicate needs he might have, so yeah, thanks for making the effort.
It is bizarre that our society now seems to reject entirely the concept of standards. If you scream at people like a crazy person then you can't go to college, full stop. Sorry, you're severely disabled and you need help you don't belong in college. Colleges are happy to collect the government subsidized tuition I guess.
If I became so disabled that I couldn't function in a social setting then please just end me. I don't want to be some vegetable that someone else needs to look after 24/7. I want to be productive, I want to be liked, I want to be free.
Whatever you are describing does not fill any of those fields. At that point I'd be complete burden and I wouldn't want that on anyone.
I've met plenty of NT people who have got too drunk or emotional in social settings and need support from others to stop making a scene. Is that functional behavior? Should they end themselves?
Your comment is very nearsighted and for some reason compares inability to "function" in a social setting with being "some vegetable" who is in a coma? What are you even talking about?
The attitude of wanting to be charge of your life and not a burden to others around you? Or did I just completely misunderstand what you tried to say? Because that doesn't make any sense at all.
You didn't say you want to be in charge of your life and not a burden. You said you'd rather want to be dead than a "burden" to others.
The way relationships especially with family works is that they'd usually rather have you be "a burden" than dead.
Also it is very hard not to project that attitude on other people who would be "a burden to others". It is hard for them not to think you want them dead or at least find them extremely worthless.
As someone who recently had to watch a family member completely deteriorate I am comfortable that mixed in with the grief was relief. Of course I would rather have them back, but knowing the condition they were in my selfishness isn't fair towards them and if anything their passing showed me that if possible I want to go out on my own terms from my two standing feet instead of bed ridden and hospitalized.
So I hope what you are saying is that this "deterioration" was genuine suffering like disease and pain, and not just some behavior or social state you believed to be burdensome on you.
But that just isn't the same. Wishing somebody to die - because of intense and hopeless suffering - is in my opinion neither something to be judged nor to be enthusiastically welcomed. I think we should ideally neither wish suffering nor death to anyone. These can become conflicting goals, when death seems to be the only relief from the suffering. As a veterinary student I have killed animals to relieve them from suffering. Veterinary professionals have some of the highest suicide rates in many countries, one suspected reason being compassion fatigue. The only way I see to avoid the emotional consequences is to try and not "wish" either death nor prolonged suffering.
There are a lot of reasons for "being a burden" that don't involve nearly as much suffering and don't instill a will to die in people. Accepting that you sometimes (and almost inevitably, with age) you become a burden to society is hard. But the perception of "burden" often ignores intangible aspects. Not everyone who "is a burden" feels depressed about it, and I don't believe all of them to be selfish.
That is why I believe "I'd rather die than be a burden" is a burden to oneself and others.
I can understand this and I respect your opinion. In my view, "not communicating and needing help 24/7" would imply a suffering distinct from just the feeling of helplessness or the desire not to be a burden. Such suffering does often lead to a wish to die, and one which may be distinct from the more psychotic wish to die ("suicidal ideation"). The latter is unfortunately much more common, and research shows it is not caused by circumstances but rather by psychiatric condition like depression. Unemployment for example, does not seem to cause suicide attempts, statistically, even though one might think there should be a correlation.
Also, I'd be careful to assume to know what I'd be feeling when I would be in such a situation. I'd be hesitant of my ability to judge for others if they'd rather have me dead, and I'd hope I would have serious misgivings in asking or wishing them to take steps in that direction.
In these things I like to apply concepts from Buddhist philosophy. Desire leads to suffering, where "desire" is more precisely defined as "wishing something that is wouldn't". Also, causing suffering or death does damage to the Karma, in Buddhist teachings. For me, this is reflected in personal experience and even some scientific findings that hurting people or even animals, does some damage to the psyche, if only in the process of getting numb to such feelings.
With the amount of effort and condescension you put into these comments picking apart a simple sentiment of "that would totally suck," it seems apparent that one thing you absolutely do not do is respect their opinion.
Maybe he behaves the way he does because there are no consequences? Like if he watches a video and screams at you to be silent, maybe snatch his device away? And then if he screams at you you all scream back at him. And if he gets violent trying to get his device back you get violent back (but only as much as needed to counteract his aggression).
But you probably want to plan this out with the other people in the group.
If you really want to continue working with him (as opposed to just leaving) you'll probably just have to stop being sensitive to the screaming and berating. He has a condition, you can either excuse yourself or just have a stronger personality. You can have fun with it, yell back but don't bully.
Some people believe their presence on the spectrum makes them superior to people who are not on the spectrum. They feel entitled to a social standing that lets them abuse others without consequence.
I can't leave. The groups were formed at the start of the semester by the professor so those are the groups that are going to last until the end of it. That's why I'm asking for advice on how to better deal with the situation.
Have you talked to your professor about it at all? That is your first avenue. Had to do this multiple times in my degree, simply because some group mates are shitty.
