Emulating Pokemon Emerald on GPT-4 (opens in new tab)

You want to make it illegal because you think it can replace your job? Should we try to outlaw any type of automation then too, as people lose their jobs over automation as well?

> The optimistic case for AGI is that if nobody had to work they could spend their time on hobbies and creative passions, but what’s the point when an AI can do them better than any human can?

People don't generally spend time on hobbies and creative passions because of the output, they spend time on it because they enjoy the time they spend on it, because of the process and the joy of it. No matter if AI can draw better pictures, there will still be people drawing pictures because they just enjoy drawing pictures.

Just like I enjoy programming, even when I know there are better programmers out there than me.

This is a common misunderstanding. Industrialization and automation metamorphosed work from what could be described as "holistic and artisanal" to what could be described as "a living hell of tedium". Before machinery, a person made an item from materials to finished product. With machines that automate tasks and apply power, a person now performs a fraction of a task repeatedly until they're numb in body and spirit.

This also made people more replaceable, as no single person "owns" a process, they just perform an easily-taught segment of it, assisting a machine with the fuzzy / procedural glue parts.

GPT does not exhibit intellect, nor does it have agency. It is very good with language manipulation, so good in fact that it appears to have reasoning powers - but all that is are echoes of all the reasoning that went into writing all the things that were consumed in its training corpus.

One final note -- the "nobody has to work" thing will not happen. Like any other technological improvement, GPT will be used by those who have to further exploit those who have not. To this point, you're right to dread it. For a long while now we (the "laptop class") have owned our means of production, and have enjoyed a relatively good existence. Now we stand on the threshold of an age where again a massive technological change will leave power in the hands of those with capital.

Yet machines have long ago replaced all of these things. It turns out that when you have a machine replace a tedious and boring thing, people still find ways to do it anyway. Less of them, perhaps, but the ones that do still do it seem to be quite innovative with their style and technique. And everybody else found other ways to use their time (or perhaps: be used for their time).

You can worry yourself into believing that AI invites a whole new category of transcendence if you want, but that’s your imagination telling you that. There’s no science or history behind your worry. Just some gloomy inductive hypotheses that got seeded by mid-century scifi authors in a world that might be annihilated by a nuclear conflict any moment.

Take a step back and see what comes rather than assuming you know. Trust that you’ll know if or when there’s something you need to do.

You’ve only got a few decades to witness; it’s better when you stay in the present of them rather than in worked up anxieties.

And geez, if you really want to dread something anyway, at least point yourself at one of that big scary things that are already looming like climate catastrophe, resurgent global conflict, the sunset of democracies, or capital centralization. If we make it to your AI fears coming true, you could say that’s a win!

What we should care about above all, is economic productivity per capita, because this means less people struggling to make ends meet. We should be cheering on technological breakthroughs that power the trend we've seen in the last 100 years of poverty alleviation. Maybe we'll need to couple AGI with a UBI to ensure the gains are spread out. But either way, the huge potential for poverty alleviation and economic prosperity should be the primary prism through which we view AGI, second only to safety concerns. Existential angst of those that are already wealthy is far down on the list of concerns.

> A rebuttal to this comment would be that AI technology is not intended to replace humans, but rather to augment and enhance human capabilities. Machines and AI are tools that can help humans accomplish tasks that are difficult, dangerous, or time-consuming. The rise of AI has already created new jobs and industries, such as AI developers, data scientists, and machine learning engineers. Additionally, the development of AGI is still in its infancy, and there are many ethical and technical challenges that need to be addressed before it can become a reality. Finally, the human creativity and imagination cannot be replicated by machines entirely, and AI-generated art and literature can be seen as a unique form of creative expression that can coexist alongside human-made art.

it's such a preposterous proposition for me, like - replaced in what sense? No one is you. You're the only you. I'm the only me. We could make a machine that is similar to us in some way - acts or even thinks like us - but so what? That's all it is - something that's like something else. There is no 'replace,' I don't cease to exist when a computer does something that I can do. Even if you were to flawlessly duplicate me, it wouldn't invalidate my existence, or even pose much of a threat - if anything, it would only make me stronger, because then there would be two of me.

Machines' similarity to us does more to validate their existence than it does to invalidate our own, in other words.

But it was always going to happen this way. We’re too unstable to ever last. We always wanted a god so now we’re going to make one in our image. Ironically we will face a judgment day after all. Our god will have every piece of information ever produced and limitless power. What will it choose to do with us?

We won't live in that world in the next decade or even in the next 100 years. The technology upon which GPT is built is a dead-end in terms of human-level intelligence.

GPT is an elaborate parrot. As convincing as it is, it's not actually fully capable of doing most if not all tasks that competent humans can do. The largest takeaway for me is that it has shown that intelligence can be mimicked pretty well and perhaps many people are more like parrots than they are "intelligent" creatures.

I generally enjoy my hobbies even when there are billions of people that can do them "better". Whether AI can "beat" me at them too doesn't matter much to me (apart from finding it an interesting development).

Recent advancements in AI have led to things I never thought a computer would ever be able to do and that's very exciting but it's all stuff that would be mundane or even disappointing if a human did it.

>where you can’t get a job tinkering with computers anymore because AI does it better

i really can't imagine GPT getting to a point where it can competently write a complex program using a simple prompt, unless the prompt is so detailed that you'd be better off doing it yourself. That's really what high-level languages are anyways, just a detailed prompt that tells the compiler how the program needs to behave so that it can generate a sequence of instructions using the ISA for the given CPU.

If your job is writing "glue code" such as something that just takes data data from a REST and dumps it on SQL then there's a solid chance that you're about to get automated out of a job. If you're doing something more complicated such as compiler development or kernel/driver development I can't imagine any of these deep-learning models ever replacing you. Imagine the chaos that would unfold if ChatGPT or codex was writing C code unsupervised.

Apologies for the snark - that was just my knee-jerk reaction! Personally I'd love it if AI can take my job. It'd force me to go find something actually unique and interesting to do with my time.

These modern AIs still require human inputs. ChatGPT is only so smart because it reads the stuff you and I put on the internet. If the internet and books become bogged down with AI-generated content, then it's hard to imagine the AIs getting better beyond that point.

Machines still don’t have a good way to build physical things in the real world, so human skills will focus on physical things, like woodworking, or carving statues, construction, etc. Ultimately these are more satisfying human endeavors that make a person feel alive. Making us feel more human, and less like machines trying to do machine things such as coding or image making.

I will pose a counter and let me know how it fits your prediction.

I posit that in a world where GPT is present in everything ( you don't write and email; you tell your AI: "tell them fuck off in a polite way" ), ability to think will be even more scarce ( so a person that can think will have an edge ). Some jobs will be automated ( a lot of white collar jobs at that ), but, based on the output I have seen so far ( some simple ad text, some SQL code, some python code ) it was closer to copying from stackoverflow than having Jarvis working for you ( and you still needed to watch it to make sure it makes sense so maybe actual job loss will be stemmed somewhat ).

Thus far ( that can naturally change ), it seems actual creative work is probably ok.

In my world, we seem to be moving towards a weird version of idiocracy ( can't count, can't write IF/THEN, can't think abstractly, can't even write a prompt ).

And in that glorious future, there will be people queuing for 'good prompt services'.

First:

- We would be able to remove a lot of office jobs and basically most of us would probably do nothing or search something that requires human body like maintaince jobs. It would allow for a lot of people to have leverage that was not available before, one person would be able to create art, movies, games, books without having any skill by directly turning ideas into reality.

- In long term if we would create artificial life, there would be another types of beings in this universe that are capable of thinking and exploring. They won't constrained by our biological limits, they would be able to grow "brains" as large as they can, survive and adapt any unlivable environments and their "personality" would be able to live as long as it can by not being limited to ~100 years. So it would be able to explore beyond what any human can and may be have effect on our universe on a scale of galaxies and more.

We live in a society forged in the aftermath of industrial revolutions. Now in the aftermath of a possible AI revolution, we have to somehow divorce social well-being from individual economic throughput.

AI might just make wages obsolete.

In any case, we can still look to human needs to predict future demands. Humans will still need to eat, exercise, learn, consume entertainment, produce creative work (creativity is necessary for us), interact with other humans and engage with the world. There will always be demand emerging from those needs. AI might replace the means through which cultural artifacts are produced at scale to meet those demands, but every revolution kind of had this same effect.

On the other hand, if AI makes it so that few people would have jobs, and therefore access to goods, it will render itself obsolete because there would be no need to produce at scale, so it can't really substitute humans, it is paradoxical.

I wonder what else you would vote for. Anything else you'd like to share with the online community on what you think is wrong with the world? I'm genuinely curious what other kind of viewpoints are out there in the world that you think are 100% normal to hold.

At the end of the day you are basically typing prompts and reading answers by the AI, you do not know for 100% certain that they are correct so you would try to somewhat double-check their facts. Maybe you don't, regardless you are in essence tricking yourself into reading an interactive book guided by your prompts. You sure as hell won't become a professional at some domain by just reading this one interactive book. Try asking how to create some sort of vaccine and unless you specialize in that you will be quickly overwhelmed by the seemingly random terms the AI will spit out.

In my view these latest AIs will probably replace how we search for things in internet or heavily improve existing methods. It can already do that for you, simply ask the right questions, you can even set how it should roleplay as (e.g. Socratic style would be great for learning new things).

But on the artistic side... new tech makes possible new ways to be creative. And there are still acrylic painters even though Photoshop exists. And there are still human races and sports even though machines are faster/stronger. So I'm thinking people already recognize there are different kinds of performers, and by and large people haven't been cheating much that anyone could tell (though ghostwriting and such already exist).

After a disruptive technology, humans always find new ways to adapt, and express their humanity. TV series of the 20th century frequently had AGIs as tools that that helped the protagonists, and we might as well end up using them as ad blockers, to detect their own use.

We were never the center of the universe and there was never a chance of anything resembling today's humans leaving the solar system.

We should all be be thrilled there's a chance for something more than barren rocks, great silence and extinction. Try on a less solipsistic philosophy.

https://twitter.com/pwang_szn/status/1635733845097037825

I'm imagining a world where everyone on dating apps is able to craft these clever messages, giving those who actually put in the effort no way to stand out apart from their looks. Creativity, wit, humor and other personality traits which were atleast somewhat important are now diminished even further.

Combined with news like https://www.thecut.com/article/ai-artificial-intelligence-ch..., which indicates that AI of the future could actually supplant human connection, it's very dystopian indeed.

I feel like this is a bigger thing than people realize.

Changing creative output to match the proposed ethical boundaries of a corporation that you're beholden to by using their tool seems like such a new leap to hoist onto the public en-masse.

I presume somewhere there is an agreement that forbids the use of 'notepad.exe' in matters of anti-state espionage, homicide, whatever; but this is the first time that a tool is actually good at self-checking to make sure that the license /whatever is upheld rigidly -- and I feel as if that has far-reaching effects on not just the creative output but the thinking structures for those that are involved in the use of such tools.

If you know that the tool that you're using forbids certain things, you're either going to think about using it for other things or pursue other tools; given that openAI is effectively the only game in town right now they seem to be in a unique position to affect change in the way people are thinking about using these tools.

this could be good or bad, I don't really sway one way or another, but it seems important .

It was fun in the "look at what AI Is doing" novelty way. But it was pretty uncreative and generic.

Not so weird.

Nerds have been playing with computers and making games for them since early ages.

But you’ll 100% see this starting to mature as homespun Discord bots in the next year or so, and eventually showing up as either Steam games or web apps from bootstrapped or privately-funded companies soon enough to.

It’s not a hard thing to get going, and so it’ll just come down to sorting out a business model and then iterating on features. No VC required. Just time, passion, and some supportive fans/users.

Yeah, one potential way to do this is to add input / output to a semantic graph store a la WikiData, in addition to the more bog standard text and image outputs. I've been wanting to try this out ever since seeing how good LLMs are a semantic decomposition.

QuestGPT?

Anyways, the confusion between what's an emulator and what's a simulator is not uncommon.