by adhocmobility on 4/8/23, 12:59 PM with 1316 comments
by HyperSane on 4/8/23, 4:13 PM
by surgical_fire on 4/8/23, 2:42 PM
It often generates code that won't compile or won'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't know that well but in languages that I am very comfortable with.
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's about it. ChatGPT has been more a hindrance than helpful in that particular domain, because I can't easily spot the flaws in its output, and I don't know in which directions to properly refine my questions.
by Aaargh20318 on 4/8/23, 1:46 PM
To make this possible we need to find a way to a new system that doesn't directly link labour with income.
by adhocmobility on 4/8/23, 2:20 PM
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 "sob" story is very harsh. This story is very real and the feeling of losing your job to automation is anything but pleasant.
by hparadiz on 4/8/23, 2:01 PM
It's silly that I have to spell it out on HN of all places. Writing code is much more complex. There's a reason we call the job "Software Engineer". GPT doesn't know what it doesn't know.
It doesn'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.
It doesn'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.
It has no idea where to retrieve the signing certificate, what format to use, or even how to generate a new one.
I can go on and on.
You're really gonna give this "AI" SSH access to your prod server and pray it doesn'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?
If you're worried about GPT taking over your job you just show your own lack of knowledge and experience.
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't predict....the whole thing falls apart.
by ricksunny on 4/8/23, 2:35 PM
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 1/10th the time it would take Priya and cost a lot less.
I doubt that she will have a job in six months."
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'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 looks correct as to go through myself de novo. And I'd have to vet each one. Even if only 1 in a hundred resulted in a wrong answer, I would need to know - which 1 of the 100?
If the article's subject starts looking for a job in 6 months, could I have the subject's contact? :)
by alchemist1e9 on 4/8/23, 1:51 PM
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.
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.
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.
by T-A on 4/8/23, 1:25 PM
1) Show Priya how to use GPT4 to do her current job in 1/10th of the time.
2) Let her use part (50%+) of the time saved to learn coding or whatever other skill she needs (not sure coding is it).
by logicalmonster on 4/8/23, 2:26 PM
2) Chaudry ignores that you need a human in the loop to check an AI's work. You don't know that an AI's answer is always right. Even if it'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'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.
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'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?
by thrdbndndn on 4/8/23, 3:54 PM
I have a remotely similar experience a few years ago, which always got me thinking.
As lots of people know, In the US at least, when you go to the gas stations to refill, you do it yourself. It's very easy, has almost no learning curve, everyone is used to it.
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's not even more convenient because you have to walk to the cashier inside to pay instead of staying at your vehicle.
I said to my parent that how "wasteful" 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 "stupid" jobs, lots of people would be unemployed.
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's workload without reducing their income. Unfortunately, we all know what actually happens: reduced workload isn't evenly distributed to workers without changing their income; instead, we just hire fewer workers with similar workload and the rest are now jobless.
I don't think it's going to change any time soon, so anyone wants to survive always has to adapt. And it's fine. But I do now have more tolerance and empathy to "worthless" jobs.
by ricardobayes on 4/8/23, 3:26 PM
by fwlr on 4/8/23, 3:10 PM
“[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….
“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.
“…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 everyone is a burden.”
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.
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.
by theusus on 4/8/23, 1:39 PM
Who will prompt the AI for code? Manager?
Also, you mentioned it gave wrong result at first. How did you know? Because you know how to code.
As mentioned in other comment she should learn more about programming so she can become indispensible.
by sholladay on 4/8/23, 2:47 PM
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.
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.
by numlock86 on 4/8/23, 5:27 PM
by rootusrootus on 4/8/23, 3:22 PM
Yesterday I asked it to give me a postgres SQL query to do something I don't often do, but I had a pretty good idea of what it would be. It confidently lied. I replied with "that is plausible but incorrect, I think you need to use X function instead" and it actually said "You're right, I'm sorry, that is the correct way to do X, here is an example". I laughed pretty hard at the casual apology followed instantly by the actually correct result. I'm in no danger of anthropomorphizing an LLM, but still.
by RecycledEle on 4/8/23, 11:05 PM
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.
In the early 1980'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.
I'm a teacher. I can see GPTs replacing text books and most teachers. I'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'm going to show them how a GPT can answer their questions, so they rarely need me.
Don'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.
by reddog on 4/8/23, 4:07 PM
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 "Learn to weld!"
by asd33313131 on 4/8/23, 4:52 PM
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.
by avion23 on 4/8/23, 1:45 PM
This is encapsulated in a sob story.
Am I wrong? I would like to hear your counter arguments
by scarface74 on 4/8/23, 1:56 PM
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.
> I don’t see a long-term career in software anymore.
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.
by satisfice on 4/8/23, 8:52 PM
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.
LLMs are incapable of doing work that requires predictability, integrity, accountability, etc.
Stop swallowing the hype, guys.
by Beaver117 on 4/8/23, 1:39 PM
by ThorsBane on 4/8/23, 3:21 PM
All of this can happen with what we now have, without compromising the social stability and social cohesion of the American Melting Pot.
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'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.
by itissid on 4/8/23, 3:08 PM
Imagine what if the Govt of India(or an organization) made Physical robotic agents for 400Million+ farmers (most of whom hold miniscule land < 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:
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.
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.
In india 6.25% of people pay income tax(https://incometaxindia.gov.in/Charts%20%20Tables/Why%20shoul...) and statistics on people who are near the poverty line are grim(though we haven't had a National census in 11+ years to really measure progress on poverty). But I have great hope for the future...
by nashashmi on 4/8/23, 3:22 PM
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.
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).
by fjcero on 4/8/23, 4:09 PM
The main issue with "AI should never existed" is kind of the same of "go to a University to learn". 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.
This will affect every industry, every career, every person. The focus on the wrong side of the coin is creating the polarization of "good vs bad". 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.
by labrador on 4/8/23, 3:16 PM
We could work on our collective waste of human cognition and talent rather than blaming it on GPT-4
by carapace on 4/8/23, 3:08 PM
Efficiency is good.
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 should be a good thing?
Her QoL would arguably be much higher if she gets to keep the pay. She would have eight hours a day to pursue science rather than drudging as a data jockey, eh?
The problem here isn't the talking computers, the problem is how to allocate the economic windfall they generate.
I've heard it said, "Let the robots do the work and we'll take their pay."
The questions are:
1) Who decides the boundaries of acceptable thought?
2) Who benefits from the economic windfall?
3) How do we educate ourselves in a world where computers can answer any (allowed) question?
by stuckkeys on 4/9/23, 2:18 AM
by visarga on 4/8/23, 5:10 PM
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.
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.
by yawnxyz on 4/8/23, 1:45 PM
by yoav on 4/8/23, 2:49 PM
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.
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.
3. Now Priya is 10x mire productive, still needed in the loop to verify her work and maintain it, and knows how to code.
4. Priya can also use GPT to help apply for any other job or help solve any other problem she’s running into locally.
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.
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)
by RobinL on 4/8/23, 1:42 PM
- 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's certainly plausible that it will become worthwhile to do more of the kind of work she already does.
- if as a society we can do biotech research faster and cheaper there may be significant benefits to human health
by brigadier132 on 4/8/23, 3:05 PM
But even so I think we can'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.
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't think so.
What's scary is that we live in the transition period and it could be messy. What comes after the "transition period" of having a world without AI to having a world with AI? I'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.
by jonnycomputer on 4/8/23, 1:55 PM
by Tycho on 4/8/23, 4:43 PM
by adnmcq999 on 4/8/23, 2:01 PM
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.
How much of this even worth fighting?
by wg0 on 4/8/23, 3:32 PM
The LLMs have no understanding whatsoever just token IDs and their probabilistic relationships with each other. I do not see them replacing 'shittiest' programmer whatsoever. Anyone writing games/software with LLM is the one who actually can code and would have produced same or better output by surely, spending more time than with an LLM.
But if you'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.
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.
by sorokod on 4/8/23, 1:44 PM
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?
by Jyaif on 4/8/23, 4:56 PM
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'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.
by michael9k on 4/8/23, 5:22 PM
Poor countries will most likely follow suit, but it will take a while.
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.
by 13years on 4/8/23, 1:55 PM
AI is unique in that it is essentially a skill/technology replication machine. What this means in reality is somewhat like ...
"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. "
Which I wrote in my longer exploration of societal impacts here - https://dakara.substack.com/p/ai-and-the-end-to-all-things
by andai on 4/8/23, 3:04 PM
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's been free for almost half a year now!
by uptownfunk on 4/8/23, 4:19 PM
Help learn about things I don’t know about. For some reason it’s better than going to the equivalent wiki.
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.
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.
The 5-10 year roadmap is then to generalize across the various domains and something approximating the feared AGI.
I am not scared of the LLMs, I am somewhat concerned we are giving these LLMs access to APIs in quite an unchecked fashion.
by knagy on 4/8/23, 2:25 PM
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.
by thih9 on 4/8/23, 4:03 PM
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?
by linsomniac on 4/8/23, 3:31 PM
by jug on 4/8/23, 5:45 PM
A guy who can code great generic stuff with GPT-4 but don'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.
by emrah on 4/8/23, 7:44 PM
It's not that it's always good, bad or anything else. It is simply inevitable.
Technology is not a living thing and it has no will. We are andromorphizing the collective behavior of lots of people. It's the people with curiosity, drive, ambition to achieve something, like build a tool that can think and perform like a brain.
So progress is inevitable because people push it forward to satisfy their own internal drives. Changing this requires changing people's drives. Given the current dominant economic model, that's close to impossible because this is exactly what it is prioritizing, contribution and progress at any cost to anyone.
by einpoklum on 4/8/23, 3:26 PM
by biql on 4/10/23, 5:39 PM
by callesgg on 4/8/23, 3:41 PM
On a societal level “work” does not generate money.
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.
“Work” generates money-transactions.
by itissid on 4/8/23, 2:55 PM
I can'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.
by electrondood on 4/8/23, 3:59 PM
by DantesKite on 4/8/23, 4:52 PM
Maybe she'll lose her job because there's only so much RNA sequence data that needs to be analyzed and fewer people can do it, but it's hard to say.
Maybe now more RNA sequence data can be analyzed and at a cheaper cost.
I wouldn't fall into despair just yet, especially since GPT-4 is still limited at a rate of 25 messages every 3 hours.
Definitely be on the lookout for changes and adapt accordingly, but be realistic about what may happen.
It can go both ways.
by kolinko on 4/8/23, 4:18 PM
The better, faster, cheaper, we can do it, the better the world will be.
by eternalban on 4/8/23, 1:49 PM
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.
Do not train your replacement
So I don't know about India, but at least in US, domain literate 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.
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.
by habibur on 4/8/23, 4:30 PM
Forget ChatGPT. If Priya didn'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.
These types of repeated regular tasks get automated, ChatGPT or not.
Interestingly in the age of Artificial Intelligence, jobs that require human "intelligence" are more likely to survive. As in spite of the name, AI really isn't that smart.
by SideQuark on 4/8/23, 2:11 PM
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.
We didn't end up with billions of jobs despite automation and invention by having people idly sit by when they could learn new tools.
by UlisesAC4 on 4/8/23, 4:09 PM
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'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.
by 999900000999 on 4/8/23, 4:07 PM
But the last 15% is making sure things actually work, and Chat GPT simply can't do that. Your friend still is going to have a job, but she'll probably be made much more productive by AI tools. We're a long ways off from actually being able to depend on these tools for any reliable type of output.
by theK on 4/8/23, 4:27 PM
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...
And that doesn't even touch the QoS topics that come with automation/ml.
by dumbfounder on 4/8/23, 1:57 PM
by weatherlite on 4/8/23, 3:25 PM
by pizza234 on 4/8/23, 3:39 PM
One would think the company will fire redundant SWEs. Nope; the company is actually hiring more. GPT-4 is increasing productivity SWEs' productivity, not replacing them.
by fsloth on 4/8/23, 4:32 PM
by hintymad on 4/9/23, 3:23 AM
by n0tahacker on 4/8/23, 3:55 PM
by jarbus on 4/8/23, 1:58 PM
by rvz on 4/8/23, 3:16 PM
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 'senior' engineers being actually less than junior; deferring to GPT-4 for everything and expecting hopelessly utopian salaries which will be certainly reduced. I'm afraid GPT-4 has fired the gun to the race to zero, with everyone (including both juniors and seniors) being affected.
Learn to adapt.
by zulrah on 4/8/23, 5:14 PM
by __NSL__ on 4/8/23, 4:44 PM
by atemerev on 4/8/23, 1:49 PM
by yashap on 4/8/23, 3:19 PM
My thoughts:
- If we ever achieve an AGI with legitimate consciousness/self-awareness/agency, I believe it will be dramatically more powerful than humans
- 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/self-awareness/agency
- 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
by tigrezno on 4/8/23, 3:40 PM
It cannot arrive soon enough for me.
by nextlevelwizard on 4/8/23, 5:41 PM
Technology marches on. Whenever there is any new technology someone loses a job, but that is not a good argument to stop technological progress.
Needs of the many and so on
by stuaxo on 4/8/23, 4:45 PM
by belter on 4/8/23, 7:32 PM
by esalman on 4/8/23, 10:32 PM
The AI generated content will scale and proliferate so much that it will put a premium on verified, curated human-generated content.
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.
by NicoJuicy on 4/8/23, 2:22 PM
I only used chatgpt for reasoning or eg. Finding synonyms for variables ( better naming).
I don't see it replacing my job, but it's a replacement for rubber ducking.
by xyproto on 4/8/23, 3:55 PM
* Telegraph Operator
* Typist / Stenographer
* Switchboard Operator
* Lamplighter
* Ice Delivery Worker
* Elevator Operator
* Film Projectionist
* Linotype Operator
* Milkman
* Coal stoker
by blobbers on 4/8/23, 5:16 PM
by nektro on 4/8/23, 4:53 PM
> I know! What a dumb thing to say, right? Technological progress is always good.
No! No! Did no one go to ethics class?
by Dreako on 4/8/23, 4:38 PM
Highly unlikely situation.
by didip on 4/8/23, 4:01 PM
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's a different topic.
by 0xbadc0de5 on 4/8/23, 3:24 PM
by DanTheManPR on 4/8/23, 3:45 PM
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.
by SquidJack on 4/8/23, 3:28 PM
by AbraKdabra on 4/8/23, 4:37 PM
by thevania on 4/8/23, 3:55 PM
by thefz on 4/8/23, 7:04 PM
by baremetal on 4/8/23, 1:36 PM
What about time after work. That is when I learned to code. In between work and going to school in fact.
by ajmurmann on 4/8/23, 3:37 PM
by cameronfraser on 4/8/23, 4:10 PM
by esrh on 4/8/23, 2:09 PM
by puttycat on 4/8/23, 4:52 PM
by totorovirus on 4/8/23, 3:29 PM
by m3kw9 on 4/8/23, 3:06 PM
by not_enoch_wise on 4/8/23, 3:06 PM
“But I need to pay rent and eat!”
Never thinking of imperial needs before themselves!
by kissgyorgy on 4/8/23, 3:16 PM
by seumars on 4/8/23, 1:37 PM
surely this is meant partly tongue-in-cheek?
by renonce on 4/8/23, 4:07 PM
by PAMANOCH on 4/8/23, 4:16 PM
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's not about to earn more or less; It's about winner takes it all. Also more specialized models trained at every profession will come.
Midjourney already completely knocked a huge amount of digital designers and workers out of their jobs. I'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'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'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.
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'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.
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.
You have enjoyed peak capitalism. You will soon need to embrace 100% of it.
by rejectfinite on 4/10/23, 2:19 PM
by Giorgi on 4/8/23, 3:21 PM
by thrownaway561 on 4/8/23, 4:18 PM
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.
as an example of how i use chatgpt to create the proposals:
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.
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
Introduction:
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.
Objectives:
The objectives of this proposal are as follows:
To deploy a scalable and reliable web application infrastructure using AWS.
To create an S3 bucket for storing static assets and media files of the web application.
To deploy three EC2 webservers to handle incoming traffic and requests to the web application.
To deploy an EC2 database server to store and manage the web application's data.
To set up an AWS VPN for secure access to the VPC and the resources within it.
AWS Infrastructure Components:
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.
Subnets: Subnets will be created within the VPC to partition the IP address range of the VPC.
Internet Gateway: An internet gateway will be created to allow access to and from the internet.
Route Tables: We will create a route table to route traffic from the internet to the web servers and the database server.
EC2 Instances: Three EC2 instances will be created to host the web application, and an EC2 instance will be created to host the database.
S3 Bucket: We will create an S3 bucket to store the static assets and media files of the web application.
Security Groups: Security groups will be created to control inbound and outbound traffic to and from the EC2 instances and the S3 bucket.
AWS VPN: An AWS VPN will be set up to provide secure remote access to the VPC.
Deployment Plan:
Create a new VPC with appropriate CIDR blocks.
Create subnets in the VPC for the web servers, the database server, and the VPN.
Create an internet gateway to allow access to and from the internet.
Create route tables to route traffic from the internet to the web servers, the database server, and the VPN.
Launch three EC2 instances to host the web application in the web server subnets.
Launch an EC2 instance to host the database in the database server subnet.
Create an S3 bucket to store the static assets and media files of the web application.
Create security groups for the EC2 instances and the S3 bucket.
Set up an AWS VPN to provide secure remote access to the VPC.
Conclusion:
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.
me ----- do a technical elaboration of the deployment plan
chatgpt4 --------- Technical Elaboration of the Deployment Plan:
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 10.0.0.0/16, which provides up to 65,536 IP addresses.
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's CIDR block range.
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's internet traffic.
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.
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.
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.
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.
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.
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.
Conclusion:
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.
by fellellor on 4/9/23, 7:45 AM
by gumballindie on 4/8/23, 2:25 PM
This sob story is proof he’s right.
by esperent on 4/8/23, 1:49 PM
Making us feel sorry for this real or imaginary Priya character who'll lose her job to AI is along the same lines as saying that we need to personally recycle to prevent climate change. It's not the solution.
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.
by cryptoegorophy on 4/8/23, 2:44 PM