I wish GPT4 had never happened

The fact that so many people fear loss of income as a result of better AI is a real indictment of our economic system. A better system that more fairly distributed economic productivity would make people welcome better AI because they could be confident it would make everyone wealthier instead of just a few people rich enough to be Goa'uld.

Funny thing - I&#x27;ve been using ChatGPT as a programming assistant. My experience with it is that the more knowledgeable I am at the domain, the more useful it is.<p>It often generates code that won&#x27;t compile or won&#x27;t run correctly, but that sort of goes in the correct direction, enough that I can spot the blunders and refine my questions. Quite often I even learn a few new things when using it to explore libraries and frameworks I don&#x27;t know that well but in languages that I am very comfortable with.<p>Now, for example, I am a lousy front end developer. Not really my area of expertise. I can do minor maintenance on an existing code base, but that&#x27;s about it. ChatGPT has been more a hindrance than helpful in that particular domain, because I can&#x27;t easily spot the flaws in its output, and I don&#x27;t know in which directions to properly refine my questions.

The big oversight here is that Priya does not want a <i>job</i>, what Priya wants is an <i>income</i>. The point of life is not working, the point of life is to enjoy it. We should strive to eliminate as many jobs as we possibly can, the less we have to work the better it is.<p>To make this possible we need to find a way to a new system that doesn&#x27;t directly link <i>labour</i> with <i>income</i>.

Hi everyone, author of the article here. I&#x27;m sorry if the article sounds overly pessimistic. I&#x27;m not making any claims with this article. I&#x27;m not proposing anything either. I do think technological progress is a good thing, even in this case. But I wrote this blog because I did have an emotional response to this technology, and wanted to pen down my thoughts.<p>Its one thing to look at a report about the economic impact of new technology, but another to experience it first-hand. This is just a story about someone who will be impacted. Calling it a &quot;sob&quot; story is very harsh. This story is very real and the feeling of losing your job to automation is anything but pleasant.

I asked GPT4 to write me a simple document. Took like 9 tries and I had to proof read it and make adjustments. And that&#x27;s with a simple paragraph in a written language. Forget about doing the header and the footer properly.<p>It&#x27;s silly that I have to spell it out on HN of all places. Writing code is much more complex. There&#x27;s a reason we call the job &quot;Software Engineer&quot;. GPT doesn&#x27;t know what it doesn&#x27;t know.<p>It doesn&#x27;t know that the unit tests broke because of the python script written for 3.5 that had an update in a dependency for 3.10 which broke backwards compatibility. Can you get it to fix the GitHub Action? Good luck.<p>It doesn&#x27;t know that the local dev environment targets WSL on Windows for the web app and an iPhone in dev mode for the mobile app.<p>It has no idea where to retrieve the signing certificate, what format to use, or even how to generate a new one.<p>I can go on and on.<p>You&#x27;re really gonna give this &quot;AI&quot; SSH access to your prod server and pray it doesn&#x27;t rm -rf the entire thing because that line happened to be in a script designed for clearing the working copy during a deploy on a load balanced box that has been deprovisioned from the target group. Really?<p>If you&#x27;re worried about GPT taking over your job you just show your own lack of knowledge and experience.<p>You can create a perfect machine to lay bricks. It could even be better then a human. But you will find that as soon as it encounters a situation it can&#x27;t predict....the whole thing falls apart.

&quot;...has a bachelor’s degree in Biotechnology and works as biomedical data curator. Her job is to go through scientific papers that publish RNA sequencing data. She understands the design of the experiment and cleans and annotates the data accordingly... Her work requires just enough domain expertise that it is been non-trivial to automate (until now).<p>I think you know where this is headed. The day I got off the GPT4 wait-list I asked it to do what Priya does on a daily basis. It got the answer wrong in the first try, but some chain-of-thought prompting and boom. GPT4 gave the correct answer in 1&#x2F;10th the time it would take Priya and cost a lot less.<p>I doubt that she will have a job in six months.&quot;<p>I am a ChatGPT4 subscriber. And I have about a 100 biomedical research papers that need going through to pull curated experiment result data from (to extrapolate into broader quantitative in vivo results). Maybe ChatGPT4 could do it. I&#x27;m afraid to try it based on other experiences with it. It would take me about as long to vet any output from ChatGPT4 that <i>looks</i> correct as to go through myself de novo. And I&#x27;d have to vet each one. Even if only 1 in a hundred resulted in a wrong answer, I would <i>need</i> to know - which 1 of the 100?<p>If the article&#x27;s subject starts looking for a job in 6 months, could I have the subject&#x27;s contact? :)

It looks like those who love LLMs (which I do) are forcing themselves to come up with narratives that mitigate the proposed negative effects.<p>I have a different suggestion. It’s likely it is real and painful and sad. Transitions are hard, disruptive and can often cause very real and negative problems, but they are unavoidable and historically technology brings humanity to a better place in the long run.<p>That reminder about printing press effects in the Ng and LeCunn video was good example. A lot of crazy bad stuff happened that likely the printing press triggered but on the other side was a Renaissance.<p>I think the narrative in this post is likely accurate. It’s not great on an individual human level and that is hard but the last possible thing we want is governments stepping in to control this situation. I don’t want to be in a global version of the Ottoman’s restricting the printing press.

&gt; GPT4 gave the correct answer in 1&#x2F;10th the time it would take Priya and cost a lot less. [...] Priya has tried to learn coding, but she has struggled. Not that she gets a lot of time to do it either.<p>1) Show Priya how to use GPT4 to do her current job in 1&#x2F;10th of the time.<p>2) Let her use part (50%+) of the time saved to learn coding or whatever other skill she needs (not sure coding is it).

1) Chaudry&#x27;s article is amazing in its lack of creative thinking. If people like Priya can be ~10 times more productive wielding some AI tools, that means that many companies can potentially produce 10 times as many products&#x2F;services and make more things that will enrich peoples&#x27; lives. Though some people in some companies might be laid off, it doesn&#x27;t necessarily mean that more people will be laid off than new jobs are created.<p>2) Chaudry ignores that you need a human in the loop to check an AI&#x27;s work. You don&#x27;t know that an AI&#x27;s answer is always right. Even if it&#x27;s perfect in 99% of cases, the answer could be jaw-droppingly destructive in that 1% of cases and make errors that even the dumbest human wouldn&#x27;t make. Being grossly wrong even a small percentage of the time is far worse than a human making minor errors sometimes, and being slow all of the time.<p>3) Go and look at some of those historical picture sites to see images of an accounting department in some companies throughout 1900s America. Before computers, you&#x27;d see a fascinating image of a gigantic floor of an office building with desks filled with typewriters and calculators and tons of workers just adding things up and trying to store records in a bunch of file cabinets. Desktop Computers and spreadsheets were invented and all of a sudden an accountant could quickly update a few values in a spreadsheet and figure out an answer to a question far faster and more reliably than that entire floor of accountants. Did accounting software make the world worse and destroy jobs even though it made 1 accountant ridiculously more productive than they were in the past?

I haven&#x27;t formed a comprehensive thought about the whole AI thing, but I can see where the author came from.<p>I have a remotely similar experience a few years ago, which always got me thinking.<p>As lots of people know, In the US at least, when you go to the gas stations to refill, you do it yourself. It&#x27;s very easy, has almost no learning curve, everyone is used to it.<p>When I went back to my home country (China), I was surprised that self-service refill is still not the norm. It exists, but in most of time, there are workers refilling for you. It&#x27;s not even more convenient because you have to walk to the cashier inside to pay instead of staying at your vehicle.<p>I said to my parent that how &quot;wasteful&quot; it is to have all these people around. They replied that, it still provide jobs despite how low skill or how low the pay is. Without these &quot;stupid&quot; jobs, lots of people would be unemployed.<p>I started to think what the ultimate purpose of work is. Sure, we can (and will, regardless how me or the author want) continue optimizing how efficient everything is, but the benefit should, at least in part, be reducing people&#x27;s workload without reducing their income. Unfortunately, we all know what actually happens: reduced workload isn&#x27;t evenly distributed to workers without changing their income; instead, we just hire fewer workers with similar workload and the rest are now jobless.<p>I don&#x27;t think it&#x27;s going to change any time soon, so anyone wants to survive always has to adapt. And it&#x27;s fine. But I do now have more tolerance and empathy to &quot;worthless&quot; jobs.

If you don&#x27;t like these fast changes, time to plan a move to more &quot;traditional&quot; countries like Italy or Spain. Apart from fiber internet, almost all tech advances were ignored for the most part: limited uber, limited airbnb, and yes you will need to call the restaurant to book a table. Even just the concept of &quot;chat support&quot; is foreign, let alone having a website for a business. There are still very many businesses without a social media presence, which would be unimaginable in North America. ChatGPT and co. will not have a significant impact in these countries. It&#x27;s the same thing - uber didn&#x27;t take away taxi drivers jobs and neither did airbnb impact hotels here (and because of regulation, it won&#x27;t).

This sentiment reminds me of Burdens. <a href="https:&#x2F;&#x2F;slatestarcodex.com&#x2F;2014&#x2F;08&#x2F;16&#x2F;burdens&#x2F;" rel="nofollow">https:&#x2F;&#x2F;slatestarcodex.com&#x2F;2014&#x2F;08&#x2F;16&#x2F;burdens&#x2F;</a><p>“[on the topic of a patient with moderate brain damage] back in the Environment of Evolutionary Adaptedness, in a nice tribe with Dunbar’s number of people, there would be no problem … he could just hang out and live in a cave and gather roots and berries and maybe hunt buffalo….<p>“But society came and paved over the place where all the roots and berry plants grew and killed the buffalo and dynamited the caves… This increased productivity by about a zillion times, so most people ended up better off. The only ones who didn’t were the ones who for some reason couldn’t participate in it… Society got where it is by systematically destroying everything that could have supported him and replacing it with things that required skills he didn’t have.<p>“…Imagine an employment waterline, gradually rising through higher and higher levels of competence. In the distant past, maybe you could be pretty dumb, have no emotional continence at all, and still live a pretty happy life. As the waterline rises, the skills necessary to support yourself comfortably become higher and higher. Right now most people in the US who can’t get college degrees – which are really hard to get! – are just barely hanging on, and that is absolutely a new development. Soon enough even some of the college-educated won’t be very useful to the system. And so on, until <i>everyone</i> is a burden.”<p>I see this happening myself as well. Part of my job as a hotel receptionist is taking bookings over the phone: in many cases I am literally just asking them questions and typing their answers into a form, exactly the same form that is available on our website. They even get the same price as if they went to our site directly. But they call up instead, because phones are within their capability to understand, while websites are definitely not. E-commerce has brought increased economic activity, but for some people it has also paved over most of the ways they are capable of performing economic activity.<p>GPT4 has raised the productivity waterline to a level where “people who blog” are now underwater, so we’re hearing about it a lot more. But it’s just an instance of the general phenomenon. Civilization has been systematically drowning the less cognitively fortunate for a few hundred years, and we should have had something in place to address this long ago.

This is a really pessimistic and shallow article.<p>Who will prompt the AI for code? Manager?<p>Also, you mentioned it gave wrong result at first. How did you know? Because you know how to code.<p>As mentioned in other comment she should learn more about programming so she can become indispensible.

Please do not disable zoom on text-based webpages.<p>maximum-scale=1, user-scalable=no is meant for apps and games that implement their own handling of the zoom gesture, e.g. to do a 3D zoom on a map that tilts the viewing perspective in addition to enlarging the map.<p>Even if you don’t have time to make your layout respond well to zoom, it’s still better to allow it. Disabling this user agent feature is extremely hostile.

People really need to accept AI as the useful tool it is and lay off the old grumpy &quot;back in my day&quot;-attitude. It&#x27;s a disruptive technology and it&#x27;s here to stay. Adapt and praise it for what it is ... and most importantly recognize what it enables you to do - instead of feeling challenged by it. Every profession that has tools that assist or take away certain aspects of it will enable you to put in more work and effort into other aspects of it. Just use that as an opportunity, like it happens every so often with every other technological advancement.

I&#x27;ve been using ChatGPT a lot. I&#x27;m no longer feeling much anxiety over the future of software engineering. GPT is a great tool. Still just a tool. It helps remind me how to do things I do rarely. To get code that exactly fits my requirements, I&#x27;d have to get so specific that I might as well just write the silly code myself. But for shell scripts, SQL, stuff like that, it&#x27;s pretty decent.<p>Yesterday I asked it to give me a postgres SQL query to do something I don&#x27;t often do, but I had a pretty good idea of what it would be. It confidently lied. I replied with &quot;that is plausible but incorrect, I think you need to use X function instead&quot; and it actually said &quot;You&#x27;re right, I&#x27;m sorry, that is the correct way to do X, here is an example&quot;. I laughed pretty hard at the casual apology followed instantly by the actually correct result. I&#x27;m in no danger of anthropomorphizing an LLM, but still.

I doubt the person the article is about will ever see this comment amount the hundreds of pages of economic and political gripes, but here is their solution anyway:<p>If your job is impacted by AI, do not give up. Learn to use the AI to do your job better. Become a 10x worker using AI.<p>In the early 1980&#x27;s, spreadsheets displaced accountants. The average accountant lost their job. The ones who came out on top over that decade learned to use spreadsheets early, and made themselves more productive. If the IRS fired everyone who was spreadsheet friendly, the recently fired spreadsheet gurus started small businesses or got jobs quickly. Eventually productivity won out over dogma, even at the IRS.<p>I&#x27;m a teacher. I can see GPTs replacing text books and most teachers. I&#x27;m going to be a 10x teacher when I go back to school in August. I will have certifications I got by studying with a GPT. I will have class modules and web sites I built using GPTs. I will be more ready than ever to help the kids. Then I&#x27;m going to show them how a GPT can answer their questions, so they rarely need me.<p>Don&#x27;t wait for an AI to take your job. Become a 10x whatever you are using AI. Priya (the person the article is about) should become a 10x biotech girl.

When automation, computers and offshoring were hollowing out the jobs of factory workers, miners and the low-to-medium skilled all we heard was &quot;Learn to code!&quot; from the laptop class of knowledge workers.<p>My advice to all the upper-middle-class professionals (teachers, lawyers, engineers, managers, accountants, doctors) out there who will soon be disintermediated by an LLM is &quot;Learn to weld!&quot;

Could Priya use chatgpt herself to do 10x bio-curations? Would this enable her to potentially set up a freelance competitor to her current employer? Could a competitor using chatgpt like that hire her to do 10x the work? Could her current employer re-deploy her somewhere else now that bio-curations are sorted out? Yes to all.<p>The author is correct, the current arrangement will change, but the opportunities will likely increase as well, not just at the macro level but in Priya’s intermediate future as well.

The Author proposes to keep worthless jobs. The same argument could be made against compilers or language translaters.<p>This is encapsulated in a sob story.<p>Am I wrong? I would like to hear your counter arguments

&gt; got the answer wrong in the first try, but some chain-of-thought prompting and boom. GPT4 gave the correct answer in 1&#x2F;10th the time it would take Priya and cost a lot less.<p>I’ve used ChatGPT to write some simple AWS automation scripts. It’s right 90% of the time after some prompting. But I still have to have enough domain knowledge to know if it’s correct. It’s just a shortcut to make me more efficient. The same is true in this case. You can’t trust ChatGPT to get it right so you still have to know what you’re doing.<p>&gt; I don’t see a long-term career in software anymore.<p>No one has a long term career in “programming”. That’s all ChatGPT is good for. After your first couple of years in the field, it becomes about translating business needs to code.

I am shocked at the lack of critical thinking about the central claim being made: that ChatGPT is able to do the girl’s job.<p>It is not able to do her job. The most charitable interpretation would be that, one time, ChatGPT did something that looks good on first inspection. But you can’t trust it. It has no accountability. It has unknowable reliability. It would be like replacing an adult with a child. Now we discover that data privacy is an issue, too, as Samsung discovered.<p>LLMs are incapable of doing work that requires predictability, integrity, accountability, etc.<p>Stop swallowing the hype, guys.

Just hurry up and automate everyone&#x27;s jobs so we can get UBI

GPT-4 will accelerate the enjoyable aspects of every job and reduce the tedious aspects. For everyone. No form of labor is excluded. GPT-4 can be hooked up to Boston Dynamics hardware to create the robots from iRobot. Every form of labor can now be automated. What this means is we have achieved universal basic income where we can now economically justify massive benefits for every citizen on the basis of completely automating everything including necessary resource extraction, refinement, and recycling. This can also now happen off-planet. We can even now build all of our computing and manufacturing needs off-planet if we want the pollution to just be space noise.<p>All of this can happen with what we now have, without compromising the social stability and social cohesion of the American Melting Pot.<p>Diversity really is our strength - pick a Synagogue, pick a Church, pick a Mosque, pick a Temple, pick a Community Center you like. Join that Community so that work and salaries aren&#x27;t your lifeblood. Learn mathematics for the sake of enjoying and understanding mathematics. Learn science for the enjoyment of it. Worship God for the enjoyment of it. Stretch the limits of apologetics and philosophy for more innovation there if you are an agnostic instead. GPT-4 will not be able to generate innovative new ideas, but it can definitely surface the best information and also automate many things. The innovation in thinking will still need to come from humans, and human-AI partnerships will always be necessary like in The Matrix.

The challenge before India is how to lift the standard of living for 500 million people to sustain the great challenges of the future including climate change.<p>Imagine what if the Govt of India(or an organization) made Physical robotic agents for 400Million+ farmers (most of whom hold miniscule land &lt; 1acre or are day laborers) specifically allowing them to do a myriad of tasks and customize them to an extent? It could eliminate major causes of poverty. The brilliance of this idea is:<p>1. Bottom up empowerment: Building such agents does not require massive supply chain and operational nightmares that other job, income creating manufacturing industries like Cars or Battery manufacturing does.<p>2. Force multiplier: This is way better than keynesian monetary ideas of just giving people money. An agent that allows you to make food, build a house and get education is infinitely better. It does not give you wealth alone it gives one hope.<p>In india 6.25% of people pay income tax(<a href="https:&#x2F;&#x2F;incometaxindia.gov.in&#x2F;Charts%20%20Tables&#x2F;Why%20should%20I%20pay%20tax.htm" rel="nofollow">https:&#x2F;&#x2F;incometaxindia.gov.in&#x2F;Charts%20%20Tables&#x2F;Why%20shoul...</a>) and statistics on people who are near the poverty line are grim(though we haven&#x27;t had a National census in 11+ years to really measure progress on poverty). But I have great hope for the future...

There is a big elephant in the room that people are ignoring. AI is coming in disrupting job flow processes (everyone sees this) And the new graduates are not equipped to enhance their work with AI (independently). The new graduates have already graduated through a curriculum based on self analysis and thought. AI will test their skills and make them obsolete. They are most at risk of structural unemployment. The advent of the Internet did the same for those who graduated right before 2000. These graduates did not have skills needed to work with the Internet. And often found themselves going back to school to learn a new trade.<p>On the other hand, there are those who graduated and have 2 yrs experience on their side have built a job independence where they can try new things like AI and modify their work process. They are well positioned.<p>The other thing people do not realize is though jobs will become quicker, quantity of jobs will be few for limited time. So imagine somebody who is testing chemicals that people up the supply chain are supplying. Now imagine that AI enhanced the testing of chemicals and sped the process, it has yet to sped up the supply. Give it a couple of years and industry will add more tests instead of reducing the amount of people who are testing. (there are no such thing as cost savings).

I empathize with the demand change on jobs that AI will create. And its really difficult to predict what the future will be, not majorly for its uncertainty but mostly because the systems thinking we need to adapt to match this new era of reasoning based on what a probabilistic model say is good or not.<p>The main issue with &quot;AI should never existed&quot; is kind of the same of &quot;go to a University to learn&quot;. We will look behind in 10-20 years and we will question why Universities were focusing in the wrong aspects of learning vs reasoning, creativity vs memorization.<p>This will affect every industry, every career, every person. The focus on the wrong side of the coin is creating the polarization of &quot;good vs bad&quot;. Which is not far from what we have today. This is beyond, this is a new way of interacting with computers that is even more human only because it commoditize things that previously were totally own for some institutions, countries, or even just not public.

<i>“I am, somehow, less interested in the weight and convolutions of Einstein&#x27;s brain than in the near certainty that people of equal talent have lived and died in cotton fields and sweatshops.”</i> - Stephen Jay Gould<p>We could work on our collective waste of human cognition and talent rather than blaming it on GPT-4

Dealing with climate change is going to be expensive.<p><i>Efficiency</i> is <i>good</i>.<p>If Priya gets to stay home and e.g. tend a Permaculture food forest while a computer does her job for her at a billionth of the cost (resource usage) that <i>should be</i> a good thing?<p>Her QoL would arguably be much higher <i>if she gets to keep the pay</i>. She would have eight hours a day to pursue science rather than drudging as a data jockey, eh?<p>The problem here isn&#x27;t the talking computers, the problem is how to allocate the economic windfall they generate.<p>I&#x27;ve heard it said, &quot;Let the robots do the work and we&#x27;ll take their pay.&quot;<p>The questions are:<p>1) Who decides the boundaries of acceptable thought?<p>2) Who benefits from the economic windfall?<p>3) How do we educate ourselves in a world where computers can answer any (allowed) question?

Priya should get the hang of the AI assistant and start using it before she falls way, way behind. It sucks for lot of people but you have to make the best of it. the future is uncertain for many of us, but we cannot give up.

I think OP is reacting too much to the implied threat of chatGPT. It&#x27;s not so good as it seems. If it does the job in 1:10 the time and still makes errors, then it might speed up productivity by a mere 2x because manual review is hard.<p>In my experience there is no task where chatGPT is 100% reliable, if it is high stakes it needs review. And chatGPT might not be best - for almost any task there is a specialised model that does it better.<p>Humans make different kinds of errors anyway, we are GPT-N level for a large value of N - so a combination of AI+human might give best results.

In the future there&#x27;ll probably be two kinds of people: the ones wielding Magic (aka LLMs)... and the ones trying to hold on to a world before Magic arrived, slowly getting eaten up by the Magic.

This is like the 5 stages of grief. You’re not seeing clearly yet some of the points you made are not what you think they are.<p>1. Give Priya GPT4 so they can be much more productive. It probably won’t be right 100% of the time. But they’ll become an expert at using it for this use case.<p>2. You said Priya has had trouble learning to code, well now she has a world class tutor to bridge the gap and learn faster and more effectively than any time in history.<p>3. Now Priya is 10x mire productive, still needed in the loop to verify her work and maintain it, and knows how to code.<p>4. Priya can also use GPT to help apply for any other job or help solve any other problem she’s running into locally.<p>5. Yes it’s true eventually humanity will be replaced by AI general intelligence but GPT4 specifically is likely to create as many new jobs as it replaces, and LLMs likely to take 10+ years to really saturate everywhere.<p>6. By the time AI replaces all jobs and it’s the doom and gloom might as well give up state you describe society will have been radically transformed and “wanting to make a lot of money as a software engineer” will likely be replaced by “AI and Robots already take care of all society’s base needs and so basic food and shelter is now free anyway and you can pursue whatever interests you have (this is likely 50-100 years away at minimum)

I don&#x27;t know how things will turn out but on the positive side two things come to mind:<p>- Priya may find work using gpt4 in her current job or in another company. Some types of work that are currently economically infeasible may become viable with a ten times speedup. It&#x27;s certainly plausible that it will become worthwhile to do more of the kind of work she already does.<p>- if as a society we can do biotech research faster and cheaper there may be significant benefits to human health

GPT4 is scary, it portends a future that many of us thought would never happen a year or two ago. We all think about the potential risks, about the kind of power this kind of mechanical intelligence can grant evil individuals or just the everyday people that will be &quot;left behind&quot;.<p>But even so I think we can&#x27;t afford NOT to have this kind of development if we want to survive as a species. If we want our lives to improve, our loved ones to live longer healthier lives. The amount of good that can come from this technology is immeasurable. The only thing we as humanity need to do is reign in our ego just like chess and go players had to do when their crafts were rendered supposedly irrelevant in the face of an insurmountable intelligence.<p>And I think the risks from AI are overblown, is AI really more dangerous than the invention of gunpowder, electricity, and of course the nuclear bomb? I don&#x27;t think so.<p>What&#x27;s scary is that we live in the transition period and it could be messy. What comes after the &quot;transition period&quot; of having a world without AI to having a world with AI? I&#x27;m not going to try to predict that but I think there are as many if not many more positive outcomes than there are negative outcomes.

Either this gets resolved, or there is going to be widespread civil discontent. Globally.

As someone who is fairly knowledgable about software engineering but doesn&#x27;t code often enough to be a super-efficient developer, I feel like GPT4 is giving me super-powers. Suddenly it doesn&#x27;t matter so much that I&#x27;m a bit rusty, or that I have the right general ideas but lack the granular expertise from experience usually needed to make quick progress.

Priya the worker getting replaced is not a tragedy in any sense other then it prevents Priya the person from helping her family and maybe realizing more lofty ambitions for herself.<p>We made computers to do our work for us and we are succeeding. But even before GPTs, there were a lot of problems with tech changing what it means to be human.<p>How much of this even worth fighting?

LLMs will be in the same limbo as the full self driving software is at the moment. Been almost a decade, thousands of miles of training and yet it cannot be trusted.<p>The LLMs have no understanding whatsoever just token IDs and their probabilistic relationships with each other. I do not see them replacing &#x27;shittiest&#x27; programmer whatsoever. Anyone writing games&#x2F;software with LLM is the one who <i>actually</i> can code and would have produced same or better output by surely, spending more time than with an LLM.<p>But if you&#x27;re clueless average desktop user, you cannot expect LLMs to churn out a full working end to end solution, not yet and probably not ever with the current probabilistic graph fitting foundations.<p>So, LLMs are surely very useful, marvellous and a handy tool in capable hands, will remain so but that Armageddon is not happening yet that you start calling for six month ban. Imagine, six months. What after six months? No answer.

There may be new jobs replacing those that have been made irrelevant by the advent of AI but Priyas and possibly some readers of this thread will nor be able to switch between them.<p>Consider a programmer that reports a productivity increase of 50% due to AI - a question the company will be asking itself is can we get rid of 50% of our programmers?

In case you find the article too long, here&#x27;s a summary by ChatGPT:<p>The author expresses initial enthusiasm about technological progress, which they believe improves our lives and generates wealth despite its job displacement effects. However, the author becomes concerned about the potential negative impact of language models like GPT4 on jobs. The author has a colleague named Priya, who comes from a poor background in India and works as a biomedical data curator. The author uses GPT4 to automate Priya&#x27;s work and is concerned that she may lose her job in the future. The author feels anxious about the implications of this technology and is uncertain about their future career prospects in software engineering. The economic impact of LLMs is unknown to the author, but they believe that some individuals will benefit greatly while others will suffer job losses.

AI will probably be the initiator for universal basic income to become widespread, at least in rich countries like the EU etc.<p>Poor countries will most likely follow suit, but it will take a while.<p>The end result, hopefully, will be a world where AI is a true benefit for the world population, but it will require a change in mindset.

We still don&#x27;t have any real understanding of how society adapts to this technology evolution. It is different than all prior technological disruptions as it has no period of adaption and stabilization to follow. It is continuous and accelerating.<p>AI is unique in that it is essentially a skill&#x2F;technology replication machine. What this means in reality is somewhat like ...<p>&quot;Climbing the skill ladder is going to look more like running on a treadmill at the gym. No matter how fast you run, you aren’t moving, AI is still right behind you learning everything that you can do. &quot;<p>Which I wrote in my longer exploration of societal impacts here - <a href="https:&#x2F;&#x2F;dakara.substack.com&#x2F;p&#x2F;ai-and-the-end-to-all-things" rel="nofollow">https:&#x2F;&#x2F;dakara.substack.com&#x2F;p&#x2F;ai-and-the-end-to-all-things</a>

&gt;Very few people truly understand the implications of this technology. Most people haven’t had a chance to try it yet.<p>Can someone explain this? People keep asking me about ChatGPT but none of them have tried it. Why? Are people too scared to even take a look? It&#x27;s been free for almost half a year now!

ChatGPT has been most useful for me to:<p>Help learn about things I don’t know about. For some reason it’s better than going to the equivalent wiki.<p>Not programming but moving through the inertia of having to write code. There’s something difficult to just getting started that chatGPT makes much much easier. However for it to be useful so far I’ve had to do significant debugging on the code but it gets me somewhere that would have otherwise taken me days.<p>I think where this goes is domain specific, because then you can really specialize and make a killer product. This is the 0-5 year roadmap.<p>The 5-10 year roadmap is then to generalize across the various domains and something approximating the feared AGI.<p>I am not scared of the LLMs, I am somewhat concerned we are giving these LLMs access to APIs in quite an unchecked fashion.

After I first encountered with GPT4, I was pessimistic about the future of my job too. Now I think it will be a productivity multiplier in the right hands (or I hope). You can get proper answers from it if you somewhat know the domain. I can ask GPT4 about programming and I get mostly what I want, but I&#x27;m useless if I have to get a decent picture from DALL-E.<p>The question is what will companies do with this productivity multiplier. My pessimistic guess would be cost cutting and letting people go. A bit more optimistic view could be better software, better test coverage, improvement in code quality, more features quicker or maybe more native applications if companies only need to develop one native app and AI can generate the app for other platforms.

&gt; GPT4 gave the correct answer in 1&#x2F;10th the time it would take Priya and cost a lot less<p>Do we know the actual price of GPT-4? I assumed they’re operating at cost and wanted to advertise the product. Is chatgpt ready to handle high volume of requests at low cost and long term?

&quot;AI isn&#x27;t coming for your job, people who leverage AI are&quot;. Priya needs to adopt GPT4 now, and become 10x more effective (by the author&#x27;s estimate). Wishing GPT4 never happened is definitely a road to being &quot;forced to move back home&quot;.

A coder should be worried about GPT-4, but not a software engineer. A software engineer is like 50% about networking and listening to client needs, requiring being attentive and with social skills (in so many meetings...) and that&#x27;s completely outside of the scope of a GPT-4 AI. The other 50% is trying to meet that as close as possible while maybe also offering ideas they didn&#x27;t think of, for added value to them.<p>A guy who can code great generic stuff with GPT-4 but don&#x27;t particularly _enjoy_ integrating it with client systems and being attentive to their particular circumstances and needs is no threat at all, at least not in the field of business that I am in and have been for the last 20 years.

&gt; What a dumb thing to say, right? Technological progress is always good.<p>It&#x27;s not that it&#x27;s always good, bad or anything else. It is simply inevitable.<p>Technology is not a living thing and it has no will. We are andromorphizing the collective behavior of lots of people. It&#x27;s the people with curiosity, drive, ambition to achieve something, like build a tool that can think and perform like a brain.<p>So progress is inevitable because people push it forward to satisfy their own internal drives. Changing this requires changing people&#x27;s drives. Given the current dominant economic model, that&#x27;s close to impossible because this is exactly what it is prioritizing, contribution and progress at any cost to anyone.

The author should rather wish wage-based-work stops happening. It was exploitative and not a necessary alternative from the get-go, and gradually it becomes more silly as more and more is mechanized and automated. Now society starts struggles to create artificial work for people to do in exchange for a salary. Stop creating &quot;jobs&quot;, start distributing products and services (and making it possible for people to pursue creative interests). But then... who am I preaching to? Most world societies are governed by rich privileged minorities, whose social position underpinned by wage-based-work (and the destitution of those who don&#x27;t submit themselves to it).

Imagine the world where everything is fully automated. You arrive at a city, order a self-driving taxi, do a self-check-in at the hotel that is managed by robots, order a food that is cooked by robots, using ingredients delivered by robots, grown in farms managed by robots. The hotel itself was 3d printed and the city district was planned by an AI algorithm optimised for economic utility. How many iterations are there before this is the reality? It would probably take a century before something like this is the norm.

People will always get lost I the system.<p>On a societal level “work” does not generate money.<p>Money exists as is and is only generated as a consequence of inequality these days. Banks inject money to compensate for the rich who won’t or can’t spend their money.<p>“Work” generates money-transactions.

I think that governments and organizations are asleep at the wheel when it comes to the unreasonable effectiveness of AI agents(virtual and physical). If Priya and 100&#x27;s of millions of people lose their incomes it stands to reason that the government&#x2F;organizations can empower these people to generate a source of sustenance using AI as well.<p>I can&#x27;t but not imagine a future where a country, lets call it Xhina, starts building robotic agents to do exactly that, where these Physical AI agents could make and fetch food, housing and provide damn good guidance on education, medical and legal issues. I would call it Good-enough AI(GAI) and its coming.

With LLMs shifting the developer&#x27;s role from imperative (writing explicit instructions) to declarative (writing the prompt and supervising the output), it seems far easier for Priya to become a productive developer, no?

It sounds like Priya is just going to be analyzing a lot more RNA sequencing data with a new tool since someone still needs to verify that it&#x27;s correct.<p>Maybe she&#x27;ll lose her job because there&#x27;s only so much RNA sequence data that needs to be analyzed and fewer people can do it, but it&#x27;s hard to say.<p>Maybe now more RNA sequence data can be analyzed and at a cheaper cost.<p>I wouldn&#x27;t fall into despair just yet, especially since GPT-4 is still limited at a rate of 25 messages every 3 hours.<p>Definitely be on the lookout for changes and adapt accordingly, but be realistic about what may happen.<p>It can go both ways.

The author seems to miss that the point of biotech is not to deliver jobs to people working in the field, but to deliver medicine and food to people.<p>The better, faster, cheaper, we can do it, the better the world will be.

I think the OP has it wrong. It won&#x27;t be millions of dollars. Try billions.<p>So in a twist of irony (considering op was written in India) here is the advice on retaining market viability in face of cheap outsourced labor.<p><i>Do not train your replacement</i><p>So I don&#x27;t know about India, but at least in US, <i>domain literate</i> workers should start companies that provide whatever they did as a unit of a corp as a service. And yes, use tools like GPT for your business.<p>You will lose the job either way. Walk out before helping in the task of setting up GPT to do your job, and start a company.

&gt; Her work requires just enough domain expertise that it is been non-trivial to automate...<p>Forget ChatGPT. If Priya didn&#x27;t struggle with coding, she could have gradually automate this task using some scripting langauge and just sit there in office and earn a living. Like many other similar stories we have heard.<p>These types of repeated regular tasks get automated, ChatGPT or not.<p>Interestingly in the age of Artificial Intelligence, jobs that require human &quot;intelligence&quot; are more likely to survive. As in spite of the name, AI really isn&#x27;t that smart.

&gt; GPT4 gave the correct answer in 1&#x2F;10th the time it would take Priya and cost a lot less.<p>So now Priya can produce far more output using GPT4 as a skilled operator, making the product she provides cheaper for others to build upon, likely expanding the market for such goods, and (as so often happens in history) resulting in more, not less, people employed.<p>We didn&#x27;t end up with billions of jobs despite automation and invention by having people idly sit by when they could learn new tools.

Well, on the other hand, her friend should be able to produce the same content in a 1&#x2F;15 or even 1&#x2F;20 of her original time.<p>The more you know about a domain the better questions you can ask to chatgpt. What people do not get is that due to lack human&#x27;s creativity it cannot innovate like a human does, it cannot create new knowledge, but it can let you know any existing field as long as you know what to ask.

In my experience with Chat GPT it usually gets things right 85% right.<p>But the last 15% is making sure things actually work, and Chat GPT simply can&#x27;t do that. Your friend still is going to have a job, but she&#x27;ll probably be made much more productive by AI tools. We&#x27;re a long ways off from actually being able to depend on these tools for any reliable type of output.

Genuine question, how does one get over the 30k token limit in a gpt4 request in such cases?<p>From my personal experience, it seems while today we can create PoCs of GPT4 doing a white colar job replacement, when you then try to actually productize it you still hit a data encoding limit...<p>And that doesn&#x27;t even touch the QoS topics that come with automation&#x2F;ml.

The way I see this is that you can feed Priya 10x as much work while you focus on higher level tasks and you make more money. Making everyone much more productive does not need to be destructive. Use this as an opportunity to scale things up, because you can clearly afford priya right now, you should be able to do more.

I think most of us wish A.I slows down. It&#x27;s simply not good for the average white collar worker. It replaces us. &quot;Things will get cheaper&quot; said the tech tycoon. Yeah that&#x27;s great, I&#x27;m unemployed and need to retrain to become a teacher or nurse at 45 but things might become cheaper...

Anecdata: at the company I work for, it&#x27;s been officially introduced GPT-4 assistance. SWEs are themselves amazed at their increase in productivity.<p>One would think the company will fire redundant SWEs. Nope; the company is actually hiring more. GPT-4 is increasing productivity SWEs&#x27; productivity, not replacing them.

This sounds like a false dichtomy. If the protagonist is adding value, letting them use chat-gpt should be viewed as increasing their value output x-fold. Chat-gpt makes mistakes and hallucinates. You will still need a human in an editorial role. But maybe I’m not understanding something obvious here.

Serious question: why are we not concerned about losing manufacturing jobs for decades? They caused great pains to our nation, right? They weakened our nation too to the point that China seems unstoppable, right? How is that job loss different than this job loss?

I wonder if the technology landscape will shift in sich a fast way that the people earning the most are the best learners. To some degree, this is already the case. But that also means that you&#x27;ll earn less when you become older and are not that good in learning anymore.

I have a suspicion that things will get much, much worse for millions of people before they get better

&gt; I don’t see a long-term career in software anymore. Any dreams I had of earning decent money as a software engineer are slowly fading. Lex Fridman in his podcast said “if you’re anxious about GPT4 its probably because you’re a shitty programmer”. I mean, I’m not the smartest in the room but I have generated value with the software I’ve made. And was convinced that I’ll make decent money as long as put in the work. I’m just not that sure anymore.<p>The flushing of the mediocre has begun. Already scared of a bullshitting sophist and Lex Friedman is correct on this. This also puts title inflation into perspective with so-called &#x27;senior&#x27; engineers being actually less than junior; deferring to GPT-4 for everything and expecting hopelessly utopian salaries which will be certainly reduced. I&#x27;m afraid GPT-4 has fired the gun to the race to zero, with everyone (including both juniors and seniors) being affected.<p>Learn to adapt.

Actually, I think we are living in the most equal times ever. Don&#x27;t get me wrong the situation is very bad especially if one belongs to any minority group but the wealth is divided more equally than any time in the history before

It is far from given that what the author predicts will happen will happen. And even if it does, this argument could have been made about any labor-saving technology in the past. “I wish Photoshop had never happened”.

Yes, the entire economy will be overhauled in next 6-12 months. The transition will be turbulent and rough. But it&#x27;s not like everyone will be out of jobs. Just the nature of their jobs will change significantly.

Job loss is one thing, but in all honesty, my main concern with AI is that it’ll wipe out humanity.<p>My thoughts:<p>- If we ever achieve an AGI with legitimate consciousness&#x2F;self-awareness&#x2F;agency, I believe it will be dramatically more powerful than humans<p>- Humans have driven countless numbers of species extinct, not because we’re trying to, but because we’re so much more powerful than them that we wipe them out by accident. They’re ants to us, we just don’t notice much about them, and IMO we’ll be ants to an AGI with legit consciousness&#x2F;self-awareness&#x2F;agency<p>- Obviously GPT4 is not that, but progress in AI has been so rapid recently that I believe we’ll get there in the relatively near future. Maybe 10 years, maybe 100, but it feels pretty likely it’s going to happen. When it does, I think humanity will be in an extremely tenuous position

AGI is humanity&#x27;s dream, our own geeni in a bottle. It will cure cancer and other diseases and probably will grant us immortality (in a form of incredible drugs without secondary issues).<p>It cannot arrive soon enough for me.

Just like horse riders and whatever lost their jobs when cars came.<p>Technology marches on. Whenever there is any new technology someone loses a job, but that is not a good argument to stop technological progress.<p>Needs of the many and so on

Get Priya on GPT4, and start producing more than you were before.

When Henry Ford proudly showed his assembly line to a union leader, the union leader reportedly asked, &quot;How are you going to get those robots to buy your cars?&quot;

I have an optimistic, almost desperate take on this.<p>The AI generated content will scale and proliferate so much that it will put a premium on verified, curated human-generated content.<p>Initially I was a ChatGPT skeptic. Then I started using it on a regular basis and unlocked more potential. Now I almost feel selfish in safeguarding my secret prompts that is helping me be productive and acquire new skills. I personally am quite confident that I will survive the AI apocalypse. But for the same reason, I am afraid for a lot of people who I know will perish.

Tbh.<p>I only used chatgpt for reasoning or eg. Finding synonyms for variables ( better naming).<p>I don&#x27;t see it replacing my job, but it&#x27;s a replacement for rubber ducking.

Here are ten examples of obsolete jobs from the past that were replaced (or nearly replaced) due to advancements in technology:<p>* Telegraph Operator<p>* Typist &#x2F; Stenographer<p>* Switchboard Operator<p>* Lamplighter<p>* Ice Delivery Worker<p>* Elevator Operator<p>* Film Projectionist<p>* Linotype Operator<p>* Milkman<p>* Coal stoker

I think the big problem is going to be corporate profits. Do you cap profits? Is it the API that makes money or custom interfaces to it?

&gt; I wish GPT4 had never happened<p>&gt; I know! What a dumb thing to say, right? Technological progress is always good.<p>No! No! Did no one go to ethics class?

Author seems to optimistic about technology adoption in places India, riddled with bureaucracy<p>Highly unlikely situation.

Ugh, with every leap of innovation and technology, everyone bemoans: Won&#x27;t you think of all these people whose jobs are gonna be lost??<p>But guess what? Life continues and new kind of jobs are created! Unemployment number is some of the lowest it has ever been. Now, you might argue that number is inaccurate, but that&#x27;s a different topic.

Ugh, those darn horseless carriages, Jacquard looms, and printing presses right?

I am begging you people to read Karl Marx&#x27;s Capital Vol 1, Ch 15: Machinery and Modern Industry<p>Do you fear washing machines because they eliminated the requirement for doing the laundry by hand? If not, then why is automation in the workplace different? We fear AI and other forms of automation in the workplace because we have no ownership or control over our economic destiny in that space.

You are saying like photoshop killed artists nothing wrong about the new tech

Am I the only one that actually wants AI to really take off? And I mean, unsupervised AI, everyone is so damn worried about AI becoming &quot;sentient&quot; they&#x27;re dumbing it down so much and I&#x27;m sitting here waiting to have personal C-3PO by my side.

adapt or die - sounds horrid but that is what made us who we are, our &quot;ecosystem&quot; is changing - who adapts will thrive, who does not, wont - sounds fair to me

It&#x27;s just going to make already rich people, richer.

&gt;Priya has tried to learn coding, but she has struggled. Not that she gets a lot of time to do it either.<p>What about time after work. That is when I learned to code. In between work and going to school in fact.

I find it frightening how views anecdotally online and from people I meet in person are more and more shifting to zero-sum. It now seems even dominant here on HN. By any objective metric (GDP, child mortality, people with college degrees, literacy, average home size) lives have gotten better. Yet everyone is focused on others having more. &quot;It&#x27;s the billionaires who are sucking up the gains, jobs moving abroad...&quot;. It seems to be blinding many people from seeing what liberalism (classical) has given us. I&#x27;m afraid we are gonna kill the golden goose and see more conflict within and between societies and countries because of the zero-sum thinking.

This article is bait and there is going to be many more articles just like it. Not even worth a discussion. The obvious answer here is to empower Priya with the tool so she can 10x herself

Thanks for the tip! Anyone wanna be my cofounder?

Completely off topic: Notion is not a good way to share text. The fact that Reader mode doesn&#x27;t work on this page is a good indicator that a lot of CSS bloat is going on.

I wish instagram and tinder never happened.

Better get Priya to learn the new tool(gpt4) to her advantage if you really want to help her, not biach about it and wish things never happened

Getting really sick of people scoffing at the privilege of being disrupted.<p>“But I need to pay rent and eat!”<p>Never thinking of imperial needs before themselves!

I 100% agree. GPT-4 just deepens the already huge gap between the richest and poorest and will raise another tech giant.

&gt;if you’re anxious about GPT4 its probably because you’re a shitty programmer<p>surely this is meant partly tongue-in-cheek?

Whenever I hear stories about someone losing jobs due to a new technology, I would say capitalism and economics rather than technology is to blame here. Yes, you lost your job, but it&#x27;s not like GPT4 made the decision to fire you, it&#x27;s your boss who found a better alternative and decided that there is no need for he&#x2F;she to pay you.

I laughed so hard at the &quot;10x times more productive -&gt; do 10x more work&quot;. One simply do not have that much work to do. I used to hire people to paint my wall in a day, now with robotics I can let the same amount of people paint my wall 10 times in a day. No. How about I fire 90% of the workers and let the last one paint the wall with the same time.<p>Make no mistake, GPT-4 is just a beginning. Far more powerful models will come, without any compromise, without any limitations. They will REPLACE your jobs, take away your income, and you will have no choice but starve after you running out of your savings inevitably. It&#x27;s not about to earn more or less; It&#x27;s about winner takes it all. Also more specialized models trained at every profession will come.<p>Midjourney already completely knocked a huge amount of digital designers and workers out of their jobs. I&#x27;m talking about a great profit wipe which is currently happening at a lightning speed across the entire digital art industry. One successful artist often needs to spend 10+ years learning to make better art. Now it&#x27;s 100% irrelevant. Every company I know is switching to Midjourney at god speed, since you do not want to be left behind. Human resources have already become a burden. You don&#x27;t even want to believe how fast the entire field is shifting to this without turning back and left countless human creators with now worthless skills in dust.<p>But remember - the current state of Midjourney is just its early stage. I fully expect its output quality completely decimate every human artist on the earth after 1-2 years, maybe 18 months, maybe even less than that. Remember AlphaGo? It&#x27;s simply on another level. You just cannot compete. Soon (1-2 years top, 12-18 months more likely) the creative industry will vanish and everyone will be forced to switch their jobs.<p>Yes, UBI will happen because people demanded it on Twitter. Make no mistake, there will be Zero protection, Zero alternative, Zero compensation from AI takeover. Billions of people out of a job, starve, die, while top companies take 100% of profit. This is the only possible outcome.<p>You have enjoyed peak capitalism. You will soon need to embrace 100% of it.

India

Stage 2 - The Anger

all i can say is that chatgpt4 has become a life saver for me. i&#x27;ve moved from programming to sales and project management. it used to take me a ton of time in order to do proposals. now i fire up chatgpt4 and just prompt it for what i need. i can reprompt it to elaborate on each section of the proposal if i want. i can now do proposals within minutes and have a library to stich together. the hardest part of sales is the paper work and chatgpt4 has eliminated that for me. i can focus on relationships with the customers and making sure my team is meeting deadlines.<p>are they award winning proposals???? Not by any means whatsoever, however, 99% of MY clients could give two sh*ts of the fine grain details of a proposal and just needs something high level with a price to begin the work.<p>as an example of how i use chatgpt to create the proposals:<p>me --- write me a proposal for creating an AWS environment consisting of 3 EC2 webservers, 1 EC2 database server and an s3 bucket all within a VPC. Include an AWS VPN for accessing into the VPC.<p>chatgpt4 --------- Proposal for Creating an AWS Environment with 3 EC2 Webservers, 1 EC2 Database Server, and an S3 Bucket in a VPC with AWS VPN Access<p>Introduction:<p>We propose to create an AWS environment that includes three EC2 webservers, one EC2 database server, an S3 bucket, and an AWS VPN for secure access to the VPC. This environment will be deployed within a Virtual Private Cloud (VPC) on the AWS platform.<p>Objectives:<p>The objectives of this proposal are as follows:<p>To deploy a scalable and reliable web application infrastructure using AWS.<p>To create an S3 bucket for storing static assets and media files of the web application.<p>To deploy three EC2 webservers to handle incoming traffic and requests to the web application.<p>To deploy an EC2 database server to store and manage the web application&#x27;s data.<p>To set up an AWS VPN for secure access to the VPC and the resources within it.<p>AWS Infrastructure Components:<p>VPC: A VPC provides a logically isolated section of the AWS cloud to launch resources in a virtual network environment. We will create a VPC with appropriate CIDR blocks to house the resources of the proposed AWS infrastructure.<p>Subnets: Subnets will be created within the VPC to partition the IP address range of the VPC.<p>Internet Gateway: An internet gateway will be created to allow access to and from the internet.<p>Route Tables: We will create a route table to route traffic from the internet to the web servers and the database server.<p>EC2 Instances: Three EC2 instances will be created to host the web application, and an EC2 instance will be created to host the database.<p>S3 Bucket: We will create an S3 bucket to store the static assets and media files of the web application.<p>Security Groups: Security groups will be created to control inbound and outbound traffic to and from the EC2 instances and the S3 bucket.<p>AWS VPN: An AWS VPN will be set up to provide secure remote access to the VPC.<p>Deployment Plan:<p>Create a new VPC with appropriate CIDR blocks.<p>Create subnets in the VPC for the web servers, the database server, and the VPN.<p>Create an internet gateway to allow access to and from the internet.<p>Create route tables to route traffic from the internet to the web servers, the database server, and the VPN.<p>Launch three EC2 instances to host the web application in the web server subnets.<p>Launch an EC2 instance to host the database in the database server subnet.<p>Create an S3 bucket to store the static assets and media files of the web application.<p>Create security groups for the EC2 instances and the S3 bucket.<p>Set up an AWS VPN to provide secure remote access to the VPC.<p>Conclusion:<p>The proposed AWS infrastructure will provide a scalable and reliable web application environment. The deployment of three EC2 instances for the web application, an EC2 instance for the database, and an S3 bucket for storing static assets and media files will ensure that the web application performs optimally. The AWS VPN will provide secure remote access to the VPC, enabling the authorized personnel to manage the resources within the VPC securely.<p>me ----- do a technical elaboration of the deployment plan<p>chatgpt4 --------- Technical Elaboration of the Deployment Plan:<p>Creating a new VPC with appropriate CIDR blocks: The first step is to create a new VPC with a CIDR block range that does not overlap with any existing networks. A CIDR block is a range of IP addresses that will be used for the VPC. In this proposed infrastructure, we will create a VPC with a CIDR block of 10.0.0.0&#x2F;16, which provides up to 65,536 IP addresses.<p>Creating subnets in the VPC for the web servers, the database server, and the VPN: Subnets will be created within the VPC to partition the IP address range of the VPC. We will create three subnets for the web servers, one subnet for the database server, and one subnet for the VPN. Each subnet will have a unique CIDR block range within the VPC&#x27;s CIDR block range.<p>Creating an internet gateway to allow access to and from the internet: An internet gateway will be created to allow access to and from the internet. The internet gateway will provide a point of entry and exit for the VPC&#x27;s internet traffic.<p>Creating route tables to route traffic from the internet to the web servers, the database server, and the VPN: A route table will be created to route traffic from the internet to the web servers, the database server, and the VPN. The route table will associate the subnets with the internet gateway and route traffic to the appropriate subnet.<p>Launching three EC2 instances to host the web application in the web server subnets: Three EC2 instances will be launched in the web server subnets to host the web application. The EC2 instances will be launched with an Amazon Machine Image (AMI) that contains the necessary software and configurations to run the web application.<p>Launching an EC2 instance to host the database in the database server subnet: An EC2 instance will be launched in the database server subnet to host the database. The EC2 instance will be launched with an appropriate AMI that contains the necessary database software and configurations.<p>Creating an S3 bucket to store the static assets and media files of the web application: An S3 bucket will be created to store the static assets and media files of the web application. The S3 bucket will be configured to be accessible only from within the VPC.<p>Creating security groups for the EC2 instances and the S3 bucket: Security groups will be created to control inbound and outbound traffic to and from the EC2 instances and the S3 bucket. The security groups will allow traffic only from specific IP addresses and ports.<p>Setting up an AWS VPN to provide secure remote access to the VPC: An AWS VPN will be set up to provide secure remote access to the VPC. The VPN will be configured to allow authorized personnel to connect to the VPC securely. The VPN will use Internet Protocol Security (IPsec) to encrypt traffic between the remote user and the VPC.<p>Conclusion:<p>The proposed deployment plan includes the creation of a VPC with subnets, internet gateway, route tables, EC2 instances, S3 bucket, and security groups. The deployment plan ensures that the web application and the database server run efficiently while maintaining security. The AWS VPN will provide secure remote access to the VPC, which allows authorized personnel to access the resources securely.

Fears of “AI” are gradually reaching mass hysteria levels at this point.

&gt; Lex Fridman in his podcast said “if you’re anxious about GPT4 its probably because you’re a shitty programmer”.<p>This sob story is proof he’s right.

The problem is systemic and ChatGPT only serves to highlight that. Wishing a new tool wasn&#x27;t invented because it further highlights deep systemic inequality is focused on the wrong thing. The deep systemic inequality is the problem. Our climate being destroyed. Our houses being bought up by megacorps and rented back to us at exorbitant rates. Our natural resources being spent with no thought to the future. And now our information being sucked up and spat out in the form of yet more profit to the megacorps.<p>Making us feel sorry for this real or imaginary Priya character who&#x27;ll lose her job to AI is along the same lines as saying that we need to personally recycle to prevent climate change. It&#x27;s not the solution.<p>The solution must be systemic change. All the profit going to huge companies while they destroy the environment, suck up natural resources, and now also informational resources in the endless cycle of greed and lack of accountability, with the only motivation being more bonuses for shareholders and executives. This cannot stand. Our societies are already breaking down. We need change.

It’s a shame I started using ChatGPT to summarize such articles: The author shares concerns about the impact of GPT-4 on jobs, specifically their friend Priya&#x27;s job as a biomedical data curator. Priya, from a poor background in Uttar Pradesh, India, sends half of her salary home to support her parents. The author tested GPT-4 on a task Priya does daily and found that it could complete the task faster and more cost-effectively. They worry that Priya and others in similar positions could lose their jobs due to the efficiency of advanced AI like GPT-4. The author also fears for their own career in software engineering, questioning the long-term prospects due to AI advancements. They lament the potential negative economic impact of large language models like GPT-4, where a few wealthy individuals may profit while others, like Priya, lose their livelihoods.