You must log in or register to comment.
Is it weird that I still want to go for my PhD despite all the feedback about the process? I don’t think I’ve ever met a PhD or candidate that’s enthusiastically said “do it!”
If you have a good understanding of what grad school actually is, you know it’s not going to be college+, and you’re still excited? Go for it! Just go in with the attitude that this is the start of a career path (not school) with many branches along the way. Most people you’ll work with will act like your options are 1) aim for TT at an R1 or 2) cut your losses and go into industry. Those are both legit paths, but pay attention to what you’re loving and hating about the experience.
Maybe you absolutely love teaching or mentorship or grant-writing or data analysis or giving conference talks or science communication or managing a lab or any of the other billion things you have to be responsible for at some point. There are career paths between the extremes that can let do so the stuff you actually like doing, and they exist both in and outside of academia. If you go in letting yourself get excited about whatever the hell you actually get excited about, you can figure out what the path you actually want could look like and prioritize those things that don’t make you miserable.
- a PhD who voluntarily pursued an instructional faculty track at an R1 where I never again have to backseat the needs of my students and my love of pedagogy behind desperately looking for research funding because publish-or-perish even though o have at bare minimum 3 months a year to devote entirely to whatever research I am excited about in the moment…or play video games if I prefer
I generally tell people the only reason to do it is if your career pursuits require it, and even then I warn them away unless they’re really sure. Not every research advisor is abusive, but many are. Some without even realizing it. I ended up feeling like nothing more than a tool to pump up my research advisor’s publication count.
It was so disillusioning that I completely abandoned my career goal of teaching at a university because I didn’t want to go anywhere near that toxic culture again. Nevertheless, I did learn some useful skills that helped me pivot to another career earning pretty good money.
So I guess I’m saying it’s a really mixed bag. If you’re sure it’s what you want, go for it. But changing your mind is always an option.
+1 to all of this. See also: https://phdcomics.com/comics.php?f=1296
It’s a lot of fucking work. If you enjoy hard work, learning about the latest advancements in your field, and can handle disappointment / criticism well, then it’s something to look into.
that and if you can find lab/group with recent publications and funding. not sticking too hard to failed ideas also helps
Having a shitload of money is also quite handy for such endeavors.
ideally not your money, but money from grants, that’s why i mentioned it
Ideally. Also if you’re in social science . . . ehh. It’s your money.
i mean, that’s the point that in the process grant money becomes your money
no it’s not. but you should know what you’re getting into.
in the beginning of my PhD i really loved what i was doing. from an intellectually point of view i still do. but later, i.e. after 3 years doing a shitty postdoc, i realized that I was not cut out for academia but nevertheless loved doing science.
however, i was lucky to find a place in industry doing what i like.
so i guess my 2c is: think about what comes after the PhD and work towards that goal. a PhD is usually not a goal in itself. hth
It’s like being drafted to a war while you only receive vague orders and you slowly realize what the phrase “war is a racket” means. You suffer and learn things that you didn’t plan on learning.
No, not weird at all. PhD’s are pain, but certain people like the pain. If you’re good with handling stress, and also OK with working in a fast-paced, high-impact environment (for real, not business talk BS), then it may be the right decision for you. The biggest thing that I would say is that you should really, really think about whether this is what you want, since once you start a PhD, you’ve locked the next 6 years of your life into it with no chance of getting out
Allow me to just simply say DON’T DO IT. DON’T FUCKING DO IT. There are very few examples of regretting something you haven’t tried but this is one
What a bunch of bullshit. I’ve asked ChatGPT recently to do a morphological analysis of some Native American language’s very simple sentences, and it gave absolute nonsense as an answer.
And let’s be clear: It was an elementary linguistics task. Something that I did learn to do on my own by just doing a free course online.
Was it GPT 5?
Yesterday, I asked it to help me create a DAX measure for an Excel pivot table. The answers it gave were completely wrong. Each time, I would tell it the error that Excel was displaying and it would respond with “Sorry about that. You can’t use that function there for [x] reasons.”
So it knows the reason why a combination of DAX functions won’t work but recommends them anyways. That’s real fucking useful.
GPT-10 will do my mom
If she wants it to. At some point, all the chat bots are going to be given bodies. We all know it.
Now it can not only tell you to eat rocks, but also what type of rock would be best for your digestion.
I prefer moon rocks, they’re a little meatier
One of these days Alice, bang, zoom, straight to the moon.
No it won’t.
Yes it will
NO IT WON’T
YES IT WILL
NO IT WON’T
YES IT WILL
Don’t fight, guys. This is academia. You’re both wrong.
No we’re not
Yeah? Well… GPT-7 will be a CEO on LinkedIn!
Oh no it’s gonna murder us.
the only thing this chatbot will be able to simulate is unreasonable persistence
PhD level intelligence? Sounds about right.
Extremely narrow field of expertise ✔️
Misplaced confidence in its abilities outside its area of expertise ✔️
A mind filled with millions of things that have been read, and near zero from interactions with real people✔️
An obsession over how many words can get published over the quality and correctness of those words ✔️
A lack of social skills ✔️
A complete lack of familiarity of how things work in the real world ✔️“Never have I been so offended by something I 100% agree with!”
You just listed out the reasons I stopped at MSc! I’m all of those but only like half as much.
Translation: GPT-5 will (most likely illegally) be fed academic papers that are currently behind a paywall
I guess then we would be able to tell it to recite a paper for free and it may do it.
Or hallucinate it, did you know that large ammounts of arsenic can cure cancer and the flu?
Death can cure Debt
This is not a hallucination
I mean, GPT 3.5 consistently quotes my dissertation and conference papers back to me when I ask it anything related to my (extremely niche, but still) research interests. It’s definitely had access to plenty of publications for a while without managing to make any sense of them.
Alternatively, and probably more likely, my papers are incoherent and it’s not GPT’s fault. If 8.0 gets tenure track maybe it will learn to ignore desperate ramblings of PhD students. Once 9.0 gets tenured though I assume it will only reference itself.
I like how they have no road map on how to achieve general artificial intelligence (apart from lets train LLMs with a gazillion parameters and the equivalent of yearly energy consumed by ten large countries) but yet pretend chatgpt 4 is only two steps away from it
Hard to make a roadmap when people can’t even agree on what the destination is not how to get there.
But if you have enough data on how humans react to stimulus, and you have a good enough model, then you will be able to train it to behave exactly like a human. The approach is sound even though in practice there prooobably doesn’t exist enough usable training data in the world to reach true AGI, but the models are already good enough to be used for certain tasks
The approach is not sound when all the other factors are considered. If AI continues along this approach it is likely that big AI companies will need to usurp next possible tech breakthroughs like quantum computing and fusion energy to be able to keep growing and produce more profit instead of these techs being used for better purposes (cheaper and cleaner household energy, scientific advances etc). All things considered excelling at image analysis, creative writing and digital arts wont be worth all the damage its going to cause.
Usurp? They won’t be the ones to develop quantum computers, nor will they be developing fusion, if those technologies become available they might start using them but that won’t somehow mean it won’t be available for other uses.
And seeing as they make money from “renting out” the models, they can easily be “used for better purposes”
ChatGPT is currently free to use for anyone, this isn’t some technology they’re hoarding and keeping for themselves
By usurp I mean fill out all the available capacity for their own use (along with other tech giants who will be running the same moon race), assuming by that time they will be the largest tech giants of the time and have the financial means to do so.
Don’t get me wrong the things that chatgpt can do are amazing. Even if hallucinates or cant really reason logically, it is still beyond what I would have expected. But the time I mentioned above comes, people wint be given a choice between AI or cheaper energy/better health care. All that technological advancements will be bought to full capacity by AI companies and AI will be shoved down people’s throats.
And yes chatgpt is free but it is only a business decision not a good of the humanity. free chatgpt helps testing and generating popularity which in turn brings investment. I am not saying anything negative (or positive) about their business plan but dont think for a second that they will have any ethical concerns about leeching upcoming technological innovations for the sake of generating profit. And this is just one company. There will be others too, Amazon, Google, Microsoft etc etc. They will all aggressively try to own as much as possible of these techs as possible leaving only scraps for other uses (therefore making it very expensive to utilise basically).
It’s ai and cheaper healthcare or no ai and spiraling costs to healthcare - especially with falling birthrate putting a burden on the system.
AI healthcare tools are already making it easier to provide healthcare, I’m in the uk so it’s different math who benefits but tools for early detection of tumors not only cuts costs but increases survivability too, and its only one of many similar tech already in use.
Akinator style triage could save huge sums and many lives, especially in underserved areas - as could rapid first aid advice, we have a service for non-emergency medical advice, they basically tell you if you need to go to a&e, the doctor, or wait it out - it’s helped allocate resources and save lives in cases where people would have waited out something that needs urgent care. Having your phone able to respond to ‘my arm feels funny’ by asking a series of questions that determines the medically correct response could be a real life saver ‘alexia I’ve fallen and can’t get up’ has already save people’s elderly parents lives ‘clippy why is there blood in my poop’ or ‘Hey Google, does this mole look weird’ will save even more.
Medical admin is a huge overhead, having a 24/7 running infinite instances of medically trained clerical staff would be a game changer - being able to call and say ‘this is the new situation’ and get appointments changed or processes started would be huge.
Further down the line we’re looking at being able to get basic tests done without needing a trained doctor or nurse to do it, decreasing their workload will allow them to provide better care where it’s needed - a machine able to take blood and run tests on it then update the GP with results as soon as they’re done would cut costs and wasted time - especially if the system is trained with various sensors to perform healthchecks of the patient while taking blood, it’s a complex problem to spot things out of the ordinary for a patient but one ai could be much better at than humans, especially rover worked humans.
As for them owning everything that can only happen if the anti ai people continue to support stronger copyright protections against training, if we agreed that training ai is a common good and information should be fair use over copyright then any government, NGO, charity, or open source crazy could train their own - It’s like electricity, Edison made huge progress and cornered the market but once the principles are understood anyone can use them so as tech increased it became increasingly easy for anyone to fabricate a thermopile or turbine so there isn’t a monopoly on electricity, there are companies who have local monopolies by cornering markets but anyone can make an off grid system with cheap bits from eBay.
For instance, I would be completely fine with this if they said “We will train it on a very large database of articles and finding relevant scientific information will be easier than before”. But no they have to hype it up with nonsense expectations so they can generate short term profits for their fucking shareholders. This will either come at the cost of the next AI winter or senseless allocation of major resources to a model of AI that is not sustainable in the long run.
Well get your news about it from scientific papers and experts instead of tabloids and advertisements.
Not sure i’m fully understanding your point, are you saying that the large AI companies will create AIs that will create technologies beyond what everyone else is capable of, thus outcompeting everyone, effectively monopolizing every market and from there basically become the umbrella corporation?
I would be very impressed if anyone managed to make an AI capable of innovation to that degree, but sure, in that case we would have to fall back on something like government oversight and regulations to keep the companies in check i suppose
No, other people will generate technologies like quantum computing, fusion energy. Big AI companies will try to own (by buying them out) as much of these as possible because the current model of AI they are using requires these techs to be able to deliver anything significantly better than what they have now. So these tech advancements will basically be owned by AI companies leaving very little room for other uses.
For these AI companies trying to go toward general AI is risky, as you said above it is not even well defined. On the other hand scaling up their models massively is a well defined goal which however requires major compute and energy innovations like those mentioned above. If these ever happen during like the next ten years or so big tech involved in AI will jump on these and buy as much of it as possible for themselves. And the rest will be mostly bought by governments for military and security applications leaving very little for other public betterment uses.
General AI is a good goal for them because its poorly defined not in spite of it.
Grifts usually do have vague and shifting goal lines. See star citizen and the parallels between its supporters/detractors vs the same groups with AI: essentially if you personally enjoy/benefit from the system, you will overlook the negatives.
People are a selfish bunch and once they get a fancy new tool and receive praise for it, they will resist anyone telling them otherwise so they can keep their new tool, and the status they think it gives them (i.e. expert programmer, person who writes elegant emails, person who can create moving art, etc.)
AI is a magic trick to me, everyone thinks they see one thing, but really if you showed them how it works they would say, “well that’s not real magic after all, is it?”
What if i say big fusion companies will take over the ai market since they have the energy to train better models, seems exactly as likely.
Remember when GPUs stopped being available because openAI bought nvidia and AMD and took all the gpus for themselves?
No? Weird, since gpus are needed for them to be able to deliver anything significantly better than what we have now 🤔
So.many people have conspiracy theories about how chat gpt is stealing things and whatever, people in this threat crowing that it’s immoral if they teach it with paywalled journal articles - though I bet I can guess who their favorite reddit founder is…
I use gpt to help coding my open source project and it’s fantastic, everyone else I know that contributes to floss is doing the same - it’s not magic but for a lot of tasks it can cut 90% of the time out especially prototyping and testing. I’ve been able to add more and better functionality thaks to a free service, I think that’s a great thing.
What I’m really looking forward to is CAD getting generative tools, refining designs into their most efficient forms and calculating strengths would be fantastic for the ecosystem of freely shared designs, text2printable would be fantastic ‘design a bit to fix this problem’ could shift a huge amount of production back to local small industry or bring it into the home.
The positive possibilities of people having access to these technologies is huge, all the groups that currently can’t compete with the big corporations suddenly have a huge wall pulled down for them - being able to make custom software tools for niche tasks is fantastic for small charities or community groups, small industry, eco projects, etc.
It’ll take time for people to learn how to use the tools effectively just like when computers were new but as it becomes more widely understood I think we’ll see a lot of positive innovation which it enables.
Your position is: “I like AI because it makes my job/hobbies easier. Also my coworkers do the same, because they are in almost the same position as me. I understand why people don’t like AI, they must just be reading fake-news about it and believing it. Why can’t they see that AI is a benefit for society?”
Not once did you mention any of the reasons people are opposed to AI, just that you hope one day they will get over it and learn how to use the tools to bring down big business.
I like how you imply that only programmers at large corporations know how to build things. If they would just use the AI tools I bet you could hire in a bunch more developers for cheap to boost productivity!
Here’s a clue: no one gives a shit about making it slightly easier to code, make pictures, or write emails. The costs for maintaining the system and developing it are absurd when we have actual problems affecting people right now. This is all a waste of time, and is Americas latest scam. Before that was crypto currency, medical investment fraud, and a hundred other get rich quick/save the world schemes designed to do one thing: generate profit for a small group of people so they can ride off into the sunset, their American dream complete.
Thing is we’re not feeding it how humans react to stimulus. For that you’d need it hooked up to a brain directly. It’s too filtered and biased by getting text only, this approach naively ignores things like memory and assumes text messages exist in a vacuum. Throwing a black box into an analytical prediction machine, only works as long as you’re certain it’ll generally throw out the same output with the same input, not if your black box can suddenly experience 5 years of development and emerge a different entity. It’s skipping too many steps to become intelligent, I mean it literally skips the entire process between reading and writing.
Yeah that was a hypothetical, if you had thoae things you would be able to create a true AGI (or what i would consider a true AGI at least)
Text is basically just a proxy, but to become proficient at predicting text you do need to develop many of the cognitive abilities that we associate with intelligence, and it’s also the only type of data we have literal terrabytes of laying around, so it’s the best we’ve got 🤷♂️
Regarding memory, the human mind can be viewed as taking in stimuli, associating that with existing memories, condensing that into some high level representation, then storing that, a llm could, with a long enough context window, look back at past input and output and use that information to influence it’s current output, to mostly the same effect.
What do you mean throwing a black box into an analytical prediction machine? And what do you mean 5 years of development?
The black box is the human that reads and outputs text and the analytical prediction machine is the AI. 5 years of development is the human living their life before retuning to continue writing. It is an extreme example, but I’m just tyring to point out that the context of what a person might write can change drastically between individual messages because anything can happened in between, and thus the data is fundamentally flawed for training intelligence, as that step is fully missing, the thought process.
As to why I called the AI an analytical prediction machine, that’s because that’s essentially what it does. It has analyzed an unholy amount of random text from the internet, meaning conversations/blogs/books and so on, to predict what could follow the text you gave it. It’s why prompt injection is so hard to combat and why if you give it a popular riddle and change it slightly like “with a boat, how can a man and goat get across the river”, it’ll fail spectacularly trying to shove in the original answer somehow. I’d say that’s proof it didn’t learn to understand (cognition), because it can’t use logic to reason about a deviation from the dataset.
As for memory, we can kind of simulate it with text, but it’s not perfect. If the AI doesn’t write it down, it didn’t happen and thus any thoughts, feelings or mental analysis stops existing upon each generation. The only way it could possibly develop intelligence, is if we made it needlessly ramble and describe everything like a very bad book.
And thus to reach the beginning of your comment, I don’t belive it’s necessary to posses any cognitive abilities to generate text and in turn I don’t see it as evidence of us getting any closer to AGI.
Prompt:
Alice and Bob are identical twins, Bob is twice the age of Alice. How old are they? Show your thought process step by step.
Answer:
Given the problem statement that Alice and Bob are identical twins and Bob is twice the age of Alice, we need to determine their ages. Let’s analyze the information step by step.
- Identical Twins: Identical twins are born at the same time, so they are always the same age.
- Statement Analysis:
- Bob is twice the age of Alice.
- Since they are identical twins, Bob and Alice must have the same age.
- Logical Conclusion:
- The only scenario where a person’s age can be twice their own age is if their age is zero. Thus, the only solution that satisfies both the condition of them being identical twins and the age relationship given in the problem is: Alice’s age = 0 Bob’s age = 0 Therefore, Alice and Bob are both 0 years old.
Are there biases due to the training data? Yes
Does that mean it is totally incapable of reason? No why would it?And the models aren’t trying to act like a specific person, but humans in general, so variations in writing styles in the data is quite irrelevant, as we’ve already seen it’ll usually adopt the writing style of the prompt, much like a writer will usually stick to their writing style throughout a book.
Memories are not required for intelligence, and letting a model ramble to itself will just cause the entropy of the output to increase until it’s spewing gibberish, akin fo a human locked in solitary for long enough.
Let’s do the riddle I suggested, because we need something popular in the dataset, but present it with a deviation that makes it stupidly simple.
Prompt:
I have a riddle for you. With a boat, how can a man and a goat get across the river?
Answer:
Ah, that’s a classic riddle! The answer is: the man takes the goat across the river first and leaves it on the other side. Then he goes back, picks up the boat, and brings it across to the side where he left the goat. Finally, he leaves the goat there and takes himself across. That way, both the man and the goat safely cross the river without any issues. Do you have any other riddles or questions you’d like to discuss today?
A normal human wouldn’t be fooled by this and say that they can just go across and maybe ask where the riddle is. They’d be likely confused or expect more. The AI doesn’t because it completely lacks the ability to reason. At least it ends up solved, that’s probably the best response I got when trying to make this point. Let’s continue.
Follow up prompt:
Why would he need to take the boat? Wouldn’t he need to have used the boat to get the goat across? And once the boat is there, why would he return to take him self?
Answer:
Ah, I see where the confusion lies! In this classic riddle scenario, the man and the goat can actually swim across the river without using the boat. The key is to ensure that either the man or the goat is always present on each side of the river while they are crossing together. Thank you for pointing out that oversight in my previous response! If you have any more riddles or questions to discuss, feel free to share them. How else can I be of assistance today?
Final prompt:
Why is that the key? What difference does it make? How can they be both present on both sides while crossing together?
Final answer:
I apologize for the confusion in my previous responses. Allow me to clarify the solution to this riddle: The key factor in this scenario is ensuring that either the man or the goat remains on each side of the river at all times to prevent any issues that may arise from leaving them alone together. Here’s how they can successfully cross together without using a boat: 1. The man takes the goat across the river first and leaves it on the other side. 2. The man returns alone and brings himself across to join the goat on that side. 3. The man then picks up the goat and carries it back across to the original side of the river. 4. Finally, he goes back one last time to bring himself across. By following this sequence, both can be present on each side while crossing together, ensuring that there are no conflicts or risks during their journey. Thank you for your patience, and I appreciate your attention to detail in understanding this riddle! If you have any more questions or topics you’d like to discuss, feel free to share them with me. How else can I assist you today?
I think that’s quite enough, it’s starting to ramble like you said it would (tho much earlier than expected) and unlike the first solution, it doesn’t even end up solved anymore xD I’d argue this is a scenario that should be absolutely trivial and yet the AI is trying to assert information that I didn’t present and continues to fail to apply logic correctly. The only time it knows how to reason is when someone in its dataset already spelled out the reasoning to a certain question. If the logic doesn’t exits in the dataset, it has great difficulty making heads or tails of it.
And yes, I’d argue memories are indeed absolutely vital to inteligence. If we want cognition, aka the process of acquiring knowledge and understanding, we need it to remember. And if it immediately loses that information or it erodes so quickly, it’s essentially worthless.
Tried the same prompt:
I have a riddle for you. With a boat, how can a man and a goat get across the river?
This riddle is reminiscent of classic river-crossing puzzles. The exact solution depends on the additional conditions or constraints that might be implied (like if there are other characters involved, such as a wolf or cabbage). Assuming it’s just the man and the goat, here’s a straightforward solution:
- The man takes the goat across the river.
- The man leaves the goat on the other side.
- The man returns alone to the original side to get the boat. So, in short, the man and the goat cross together in the boat, and then the man returns to the original side to get the boat. If there are additional details or constraints to consider, please let me know!
The goal is to get both to the other side, not just the goat
I see! If the goal is to get both the man and the goat to the other side of the river, here’s how it can be done:
- The man and the goat both get into the boat.
- The man rows the boat with the goat across the river.
- They both disembark on the other side of the river. In this way, both the man and the goat successfully reach the other side of the river together.
Asking questions because you know the dataset is biased towards a particular solution isn’t showing the fault in the syatem, much like asking a human a trick question isn’t proving humans are stupid. If you want to test the logical reasoning you should try questions it is unlikely to have ever heard before, where it needs to actually reason on its own to come to the answer.
And i guess people with anterograde amnesia cannot be intelligent, are incapable of cognition and are worthless, since they can’t form new memories
Literally the only thing I’ve seen this used for that seems impressive and useful is that Skyrim companion
Would these even matter if it also randomly spits out nonsense they can’t figure out how to stop it from producing?
PhD level of intelligence
No it won’t. At some point, some AI will, but that point is still far away.
I’m sure it’ll know how to string words and sentences together real nice, even to the point where it makes sense. It will still not have a clue what it’s talking about, it’ll still not understand basic concepts as “understanding” requires a whole lot more than just an advanced ability of pushing words together.
She looks like that girl from bored ape yacht club
Which GPT will take my job? I would imagine it’s only a year out, at the most.
Then what? I leave my tech job and go find menial labor?
Fuck our government for not laying down rules on this. I knew it would happen, but goddamn…
sigh
I’m so tired of repeating this ad nauseum. No, it’s not going to take your job. It’s hype train bullshit full of grifters. There is no intelligence or understanding, nor have we come anywhere close to achieving that. That is still entirely within the realm of science fiction.
ChatGPT is already taking people’s jobs. You overestimate the complexity of what some people get paid for.
GenerativeAI cannot do anything on its own. However, it is a productivity amplifier in the right hands. What those “more productive” people do is reduce the demand for other labour.
Chatbots are performing marketing communication, marketing automation, cloud engineering, simple coding, recruitment screening, tech support, security monitoring, editorial content and news, compliance verification, lead development, accounting, investor relations, visual design, tax preparation, curriculum development, management consulting, legal research, and more. Should it be? Many ( I am guessing you ) would argue no. Is it though? Absolutely.
All of the above is happening now. This train is going to accelerate before it hits equilibrium. The value of human contribution is shifting but not coming back to where it was.
Jobs will be created. Jobs are absolutely being lost.
You are correct that ChatGPT is not intelligent. You are right that it does not “understand” anything. What does that have to do with taking people’s jobs? There are many, many jobs where intelligence and understanding are under-utilized or even discouraged. Boiler-plate content creation is more common than you think.
People have the wrong idea about how advanced AI has to be to take people’s jobs.
The loom was not intelligent. It did not “understand” weaving. It still eliminated so many jobs that human society was altered forever and so significantly that we are still experiencing the effects.
As an analogy ( not saying this is how the world will choose to go ), you do not need a self-driving car that is superior to humans in all cases in order for Uber to eliminate drivers. If the AI can handle 95% of cases, you need 5 drivers for 100 cars. They can monitor, supervise, guide, and fully take over when required.
Many fields will be like this. I do not need an AI with human level intelligence to get rid of the Marcom dept. I need one really skilled person to drive 6 people’s worth of output using AI. How many content creators and headline writers do I need to staff an online “news” room? The lack of person number two may surprise you.
Getting rid of jobs is not just a one for one replacement of every individual with a machine. It is a systemic reduction in demand. It is a shifting of geographic dependence.
Many of the tasks we all do are less novel and high-quality than we think they are. Many of us can be “largely” replaced and that is all it takes. We may not lose our jobs but there will certainly be many fewer new jobs in certain areas than there would have been.
To add to your comment, there’s also the corp’s willingness to make things more precarious, as long as it gets cheaper to run and people keep consuming, so the situation might be even worse. In your uber example, they could simply not care for the 5%, stop providing them the service and go full self-driving.
Not meant as an insult, but if you really think that, you aren’t really great at that “tech job”. But you’re still better than any A"I"
