The ChatGPT AI considers the future of work and FIRE

[Ron Scott]

AI advancements are making headlines and I though it would be fun to ask the latest & greatest its thoughts on how AI advances will affect work and FIRE:


How might advanced Als with capabilities such as ChatGPT transform work in wealthy countries as we know it today?

Advanced Als like ChatGPT have the potential to greatly transform the way work is done in wealthy countries. They can automate many tasks that are currently performed by humans, leading to increased efficiency and productivity. This can lead to the displacement of certain jobs, but also the creation of new, more complex and higher-skilled jobs in fields such as Al development and management. Additionally, Als can also assist workers in tasks such as data analysis, decision making, and communication, allowing them to focus on more creative and higher- level tasks. However, it is important to also consider the ethical implications of widespread Al adoption in the workplace, such as job displacement and the need for retraining and re-education programs.


Which jobs specifically are most likely to be eliminated and how might this affect people currently working in those jobs?

Jobs that are most likely to be eliminated by the widespread adoption of advanced Als like ChatGPT are those that involve repetitive tasks, simple data analysis, and basic decision making. These types of jobs are often referred to as "routine" jobs. Examples of jobs that fall into this category include:
•Data entry and data processing jobs
•Telemarketing and customer service jobs
  Manufacturing jobs, particularly those involving assembly line work
• Transportation jobs, such as truck and taxi drivers
Retail jobs, such as cashiers and stock clerks
The elimination of these jobs can have a significant impact on the people currently working in them. They may struggle to find new employment, especially if they lack the skills and education needed for more advanced jobs. This could lead to increased unemployment, underemployment, and economic hardship for affected individuals and communities. It is important for governments, companies, and other organizations to consider these potential impacts and implement policies and programs to support those affected by a transition to a more automated workplace.


Given the composition of the US workforce now, how many workers are likely to be displaced by such Al?

It is difficult to provide an exact number of workers in the US that are likely to d be displaced by advanced Als like ChatPT, as it will depend on the rate of adoption of the technology, the specific industries and jobs that are impacted, and the effectiveness of retraining and re-education programs.
However, some estimates have been made based on research and analysis of the current composition of the US workforce.
A 2017 study by the McKinsey Global Institute estimated that as many as 800 million jobs worldwide could be displaced by automation by 2030, although this is a global figure.
A 2018 report by the Center for Global Policy Solutions estimates that up to 25% of jobs in the US could be at risk of displacement by Al and automation.
A 2020 analysis by the Brookings Institution estimated that around 36 million workers in the US, or roughly 25% of the workforce, are at high risk of having their jobs impacted by Al and automation.
It is important to note that these are estimates and the actual number of
workers impacted could be different. The actual number will also depend on
how quickly the technology develops and how quickly it is adopted across different sectors. Furthermore, it is important to note that Al will also create new jobs and opportunities.


In light of such changes to the workforce in an Al-driven world, describe the 5 most important changes a young person hoping to retire early in their lives can make to best ensure they have a chance to do so.

1. Develop in-demand skills: As the nature of work evolves with the adoption of advanced Als, it will become increasingly important to have skills that are in high demand. This could include technical skills in areas such as data science, machine learning, and programming, as well as soft skills such as problem-solving, critical thinking, and communication.
2. Embrace lifelong learning: The pace of technological change is only going to accelerate, so it's important to be prepared to continuously learn new skills and adapt to new job roles. This will help ensure that your skills remain relevant in an ever-changing job market.
3. Create multiple streams of income: The traditional 9-to-5 job may become less common as automation and Al take over certain tasks. To increase your chances of retiring early, it's important to explore other ways to earn money, such as starting a business, investing in real estate, or creating a passive income stream.
4. Be adaptable: As the job market evolves, it's important to be open to change and willing to adapt to new opportunities. This may mean relocating, switching industries, or taking on a job that is different from what you've done in the past.
5. Start saving and investing early: Even with the uncertainty that comes with an Al-driven world, the importance of saving and investing early remains the same. The earlier you start saving, the more time your money has to grow and the more flexibility you will have to adapt to changes in the job market.
It is important to note that these are general suggestions and the actual steps you should take will depend on your personal circumstances and goals. It's always a good idea to consult with a financial advisor to create a personalized plan that takes into account your unique situation.

[Scandium]

So it's a bot that scrapes the internet for tech-bro and thinktank answers? With the pre-requisite upper-middle class privilege tilt to the solutions. Cool

[ChpBstrd]

I don't know much about ChatGPT, but a lot of my predictions from 20 years ago seem comical today, despite the technology now being to the point I thought they'd come true:

1) I thought physical universities and colleges would be replaced by online colleges that charged a tiny fraction of the cost.
2) I thought there would be no more paper books by now.
3) I thought there would be ground-based drones, such as remote controlled full sized tanks or farm equipment.
4) I never thought Segways would become people's primary mode of transportation, as was popular to believe at the time, but I thought they'd sell better than they did. Instead the gasoline-powered redneck dunebuggy market went crazy.
5) I thought all cars would be hybrids by now, and gasoline would be $10-20/gallon.
6) I thought my coaxial cable internet service would be obsolete by now. Instead it got a lot faster.
7) I thought netbooks (8-11" screen low-power laptops) would be a bigger thing.
9) I figured the work-from-home movement would have started by about 2010, when the tech was more than sufficient to support it.
10) I thought we'd all be doing our taxes on the IRS' website, or more accurately, reviewing our already-completed forms.

For 100% of these things, the necessary tech exists, or has existed for a long time, for my predictions to come true. People's behavior, however, is what made the possible into a nothingburger. The demand was just not there for certain things.

My predictions now are that customer service and administrative jobs are in definite danger, but the rest will depend on what people decide they want. E.g. An A.I. restaurant waiter might ruin the experience and never take off. An A.I. troubleshooting tool might only be good at identifying known issues, which you might as well go and fix rather than investing in a A.I. troubleshooting tool to find them over and over again. Etc.

My other prediction is that A.I. will speed up the pace at which businesses change themselves. This is based on my observation of how my company responded to automation tools. We didn't accept the higher efficiency and rest on our laurels! Now we get a new business process for key tasks every few months, and our clients change their contracts with us at a similar frequency. The old days of making one model of thing or proving a consistent service for a year might be over, because flexible automation both lowers the cost of change and lowers the cost of quality. Now we have an entire department of people to change the algorithms for other departments. Now our contracts specify that we have to regularly change our deliverables at our clients' whims, and the expectation is we do it for free. If we refused, the work would go to someone who can accept those terms.

[Ron Scott]

I don’t think you can expect too much from these early bots. But investors are pouring a fortune into this stuff and after ChatGPT’s release the CEO of Google issued a “code Red” in the company, to fast-track responses to what he sees as a real challenge to the business. So you can expect AI to continue to improve and pop up all over.

Re: jobs, robots are already augmenting manufacturing in ways that only humans could do before, and even those horrible customer service bots have replaced hundreds of thousands of reps so it’s probably real.

But I think the guy who places all the Happy Meal item in the bag is safe for a few more years! We shall see.

[electriceagle]

Within the past month, Microsoft has laid off about 10,000 programmers and the AI company that it owns, Open AI, has hired cheap contractors in low-cost locations like Latin America and Eastern Europe to create a dataset that AI can use for programming. Specifically, they have been hired to label snippets of code so that the AI will "understand" them and be able to use them.

https://www.semafor.com/article/01/27/2023/openai-has-hired-an-army-of-contractors-to-make-basic-coding-obsolete

A software developer in South America who completed a five-hour unpaid coding test for OpenAI told Semafor he was asked to tackle a series of two-part assignments. First, he was given a coding problem and asked to explain in written English how he would approach it. Then, the developer was asked to provide a solution. If he found a bug, OpenAI told him to detail what the problem was and how it should be corrected, instead of simply fixing it.

“They most likely want to feed this model with a very specific kind of training data, where the human provides a step-by-step layout of their thought-process,” said the developer, who asked to remain anonymous to avoid jeopardizing future work opportunities. He has not yet been hired or rejected by OpenAI.

I expect that top-quality coders will continue to be in demand but that medium-quality programmers, who represent the vast majority of programmers, are going to have a hard time.

I'm on vacation in the Philippines right now. I'm in Manila (don't worry, just here to get out of jetlag -- we'll go someplace beachier in a moment) looking out my window at a tall building with "Accenture" on it. Most of this stuff was not here when I visited the Philippines for the first time about 10 years ago. I suspect that a large portion of the economic development in developing world capitals like Manila, Mumbai, etc. over the past 20 years has been driven by the replacement of medium-quality western professionals with medium-quality developing world professionals.

There are some top quality programmers in each of these locations, but I suspect that there is a skew relative to the western world because of differences in depth of knowledge that are themselves driven by differences in education and early technology experience. Imagine someone who has been riding some sort of bike since they were 7 years old versus someone of the same innate ability who started in college when they were 18. Who will win the Tour de France.

If AI-driven written task completion takes off, it could severely disrupt developing world economies that need professionals who are employed serving the outside world. A contraction in the knowledge worker economy that mirrors the (United States) contraction in the manufacturing economy between 1980 and 2010 would set labor-export economies back severely.

This means conflict, and a lot of it. The standard response from political leaders in trouble is to engineer fights between groups within the population. Stoking racial and religious conflict, and stirring up moral panics, are top ways that political leaders keep the public from ejecting them. Consider the various racial, gender, and anti-immigrant conflicts that have been stoked over the past 30 years as the median inflation-adjusted income in the US has either decreased or flatlined. Consider the racial and tribal conflicts that leaders in high visible-corruption countries rig up to keep the public off their backs. Imagine what happens when a nation's professionals -- who are supporting their extended families because they are nearly all the first in their families to become profesionals, and are the nation's main source of hard currency -- find themselves out of work over a much shorter time period. Could get ugly.

The second big question is what happens when the return on education becomes too small to make it advisable. Most knowledge workers (back to western countries here) spend 4-6 years in university after secondary school to learn the concepts behind a profession and expect to get 20-30 years (more for those who become leaders in their professions) of good-paying work out of it. What happens when the return on 4 years of college for the average (by definition mediocre) professional is just 10 years of work... or just 5. Sure, the superstars will still do well, but most people aren't superstars. You can't train your way out of it, as your human competition is retraining too and some of them will train the AI to do your new job.

Keep your hat on. Its going to be a wild ride.

[scottish]

But investors are pouring a fortune into this stuff...

That's because it costs a fortune to develop a state of the art neural network.    You need a team of domain experts and a team of "deep learning" experts and a huge amount of processing time...

[ChpBstrd]

I expect that top-quality coders will continue to be in demand but that medium-quality programmers, who represent the vast majority of programmers, are going to have a hard time.

...I suspect that a large portion of the economic development in developing world capitals like Manila, Mumbai, etc. over the past 20 years has been driven by the replacement of medium-quality western professionals with medium-quality developing world professionals.

I suspect there are generational cycles where a shortage of workers in a particular job makes for high wages and great job security, but then everyone flocks to that job just as technology makes the job less important.

Decades ago, a generation of Americans worked manufacturing jobs in union plants. With world-leading wages, they were able to own houses, have kids, buy a car or two, retire early on pensions, etc. They encouraged their kids to do the same. But by the time their kids got into manufacturing, it was being off-shored, and robotic equipment was taking over the old put-the-nut-on-the-bolt work

Just a couple decades ago, a generation of Americans earned world-leading wages doing IT work like setting up company network drives, setting up networked printers, and configuring servers to run it all. They encouraged their kids to do the same. But by the time their kids got into IT, the printers were gone, the servers had all been migrated to the lower-maintenance cloud, and GUI-based tools like Wordpress, Wix, Salesforce, etc. had converted once-technical jobs to tasks end users could perform. Computers became leased items nobody bothered to fix or upgrade anymore. The few things that didn't work out of the box as SAAS could be fixed remotely by offshored consultants. People with skills like html, RAID arrays, or hardware had to quickly retrain for the remaining jobs. At some point, it seems the writing is on the wall that IT will consume itself by becoming more and more a set of packaged finished products that doesn't require an army of "IT guys" to run every company.

For a long time now, people have made world-leading wages doing knowledge work. They said "factories may have replaced workers with robots, but they will never be able to replace lawyers / doctors / engineers / artists / top-tier programmers / professors because these are jobs doing what machines will never be able to do." Well... now with every ChatGPT response I see, it seems like those knowledge jobs are becoming more and more shaky. It already seems old fashioned to think AI can't possiibly field customer service calls, identify cases with legal precedent, design a bridge, create a painting, pilot a vehicle, or diagnose an illness. If AI does for these jobs what factory robots did for manufacturing jobs, and what cloud computing did for IT jobs, then what is left? Don't say prostitution, because there are already robots for that which are cheaper, more compliant, and safer than humans.

This all means it's even more urgent to start living off our capital rather than our labor. I'd rather own a piece of the machines that take my job than fight everybody else for the ever-narrowing range of jobs the machines still can't do.