Leaked Documents Show OpenAI Has a Very Clear Definition of ‘AGI’

it would be quite trope inversion if people sided with the ai overlord

For fun, I used this idea in chatgpt using similar logic:

Hello, can you explain to me how a strict profit generated number would result in a specific goal, such as if I make 1000 dollars I would suddenly be capable of owning a house. I find the idea strange and backwards.

You're correct to find this idea odd—it reflects a misunderstanding of how financial goals, like owning a house, relate to income. Here's why this thinking is flawed:

1. Profit vs. Net Worth: Making $1,000 in profit doesn't directly equate to being able to afford a house because buying a house requires not just income but also savings, creditworthiness, and a down payment. Profit is only a small piece of the puzzle.

2. Costs and Expenses: Owning a house involves more than just the purchase price. You need to consider closing costs, property taxes, maintenance, and potentially ongoing mortgage payments. $1,000 would likely not be enough to cover even a fraction of these.

3. Leverage and Financing: Most people don't buy houses outright; they use loans or mortgages. To secure a mortgage, lenders look at your total financial picture: income, savings, debt, and credit score. Simply generating $1,000 won't improve these factors significantly.

4. Specificity of the Goal: "Making $1,000" is a general financial milestone, not a specific strategy tailored to the requirements of owning a home. A more actionable goal would involve budgeting, saving for a down payment, and improving credit.

5. The Backwards Logic: The idea that reaching an arbitrary profit threshold suddenly makes you eligible for something like owning a house conflates short-term gains with long-term financial stability. A better approach is to reverse-engineer the goal: start by determining the total cost of the house, then work backwards to figure out how much you need to save monthly, how much income you need to earn, and what steps are required to secure financing.

Example of Goal-Oriented Thinking:

If you wanted to own a $200,000 house:

You might need a 10% down payment ($20,000).

Closing costs could add $5,000–$10,000.

Monthly income would need to support a mortgage payment (let’s say $1,200/month).

Steps would include saving regularly, reducing debt, and improving credit, rather than focusing on an isolated profit milestone like $1,000.

Summary:

Focusing on a single, arbitrary profit number like $1,000 doesn’t align with the comprehensive planning required for significant financial goals like home ownership. Instead, success depends on a holistic view of your finances and structured goal-setting.

The same way these capitalists evaluate human beings.

Guess we're never getting AGI then, there's no way they end up with that much profit before this whole AI bubble collapses and their value plummets.

That's an Onion level of capitalism

The context here is that OpenAI has a contract with Microsoft until they reach AGI. So it's not a philosophical term but a business one.

I’m pretty sure the simplest way to look at is an LLM can only respond, not generate anything on its own without prompting. I wish humans were like that sometimes, especially a few in particular. I would think an AGI would be capable of independent thought, not requiring the prompt.

There are already a few papers about diminishing returns in LLM.

I hope someone will finally mathematically prove that it's impossible with current algorithms, so we can finally be done with this bullshiting.

They did! Here's a paper that proves basically that:

van Rooij, I., Guest, O., Adolfi, F. et al. Reclaiming AI as a Theoretical Tool for Cognitive Science. Comput Brain Behav 7, 616–636 (2024). https://doi.org/10.1007/s42113-024-00217-5

Basically it formalizes the proof that any black box algorithm that is trained on a finite universe of human outputs to prompts, and capable of taking in any finite input and puts out an output that seems plausibly human-like, is an NP-hard problem. And NP-hard problems of that scale are intractable, and can't be solved using the resources available in the universe, even with perfect/idealized algorithms that haven't yet been invented.

This isn't a proof that AI is impossible, just that the method to develop an AI will need more than just inferential learning from training data.

The only text predictor I want in my life is T9

I just tried Google Gemini and it would not stop making shit up, it was really disappointing.

Roger Penrose wrote a whole book on the topic in 1989. https://www.goodreads.com/book/show/179744.The_Emperor_s_New_Mind

His points are well thought out and argued, but my essential takeaway is that a series of switches is not ever going to create a sentient being. The idea is absurd to me, but for the people that disagree? They have no proof, just a religious furver, a fanaticism. Simply stated, they want to believe.

All this AI of today is the AI of the 1980s, just with more transistors than we could fathom back then, but the ideas are the same. After the massive surge from our technology finally catching up with 40-60 year old concepts and algorithms, most everything has been just adding much more data, generalizing models, and other tweaks.

What is a problem is the complete lack of scalability and massive energy consumption. Are we supposed to be drying our clothes at a specific our of the night, and join smart grids to reduce peak air conditioning, to scorn bitcoin because it uses too much electricity, but for an AI that generates images of people with 6 fingers and other mangled appendages, that bullshit anything it doesn't know, for that we need to build nuclear power plants everywhere. It's sickening really.

So no AGI anytime soon, but I am sure Altman has defined it as anything that can make his net worth 1 billion or more, no matter what he has to say or do.

Lol. We’re as far away from getting to AGI as we were before the whole LLM craze. It’s just glorified statistical text prediction, no matter how much data you throw at it, it will still just guess what’s the next most likely letter/token based on what’s before it, that can’t even get it’s facts straith without bullshitting.

This is correct, and I don't think many serious people disagree with it.

If we ever get it, it won’t be through LLMs.

Well... depends. LLMs alone, no, but the researchers who are working on solving the ARC AGI challenge, are using LLMs as a basis. The one which won this year is open source (all are if are eligible for winning the prize, and they need to run on the private data set), and was based on Mixtral. The "trick" is that they do more than that. All the attempts do extra compute at test time, so they can try to go beyond what their training data allows them to do "fine". The key for generality is trying to learn after you've been trained, to try to solve something that you've not been prepared for.

Even OpenAI's O1 and O3 do that, and so does the one that Google has released recently. They are still using heavily an LLM, but they do more.

I hope someone will finally mathematically prove that it’s impossible with current algorithms, so we can finally be done with this bullshiting.

I'm not sure if it's already proven or provable, but I think this is generally agreed. just deep learning will be able to fit a very complex curve/manifold/etc, but nothing more. It can't go beyond what was trained on. But the approaches for generalizing all seem to do more than that, doing search, or program synthesis, or whatever.

I mean, human intelligence is ultimately too "just" something.

And 10 years ago people would often refer to "Turing test" and imitation games in the sense of what is artificial intelligence and what is not.

My complaint to what's now called AI is that it's as similar to intelligence as skin cells grown in the form of a d*ck are similar to a real d*ck with its complexity. Or as a real-size toy building is similar to a real building.

But I disagree that this technology will not be present in a real AGI if it's achieved. I think that it will be.

I'm not sure that not bullshitting should be a strict criterion of AGI if whether or not it's been achieved is gauged by its capacity to mimic human thought

It's impossible to disprove statements that are inherently unscientific.

What is your brain doing if not statistical text prediction?

The show Westworld portrayed it pretty good. The idea of jumping from text prediction to conscience doesn't seem that unlikely. It's basically text prediction on a loop with some exterior inputs to interact.

this is almost a haiku

Cars, and snake oil, and propaganda

Then we untaught it to do math.

https://medium.com/tomorrows-jobs-today/why-chatgpt-cant-do-basic-math-fc1a132e9773

Oh yeah!? If I'm so dang smart why am I not generating 100 billion dollars in value?

So then how do we define natural general intelligence? I'd argue it's when something can do better than chance at solving a task without prior training data particular to that task. Like if a person plays tetris for the first time, maybe they don't do very well but they probably do better than a random set of button inputs.

Likewise with AGI - say you feed an LLM text about the rules of tetris but no button presses/actual game data and then hook it up to play the game. Will it do significantly better than chance? My guess is no but it would be interesting to try.

Any or every task?

So if you give a human and a system 10 tasks and the human completes 3 correctly, 5 incorrectly and 3 it failed to complete altogether... And then you give those 10 tasks to the software and it does 9 correctly and 1 it fails to complete, what does that mean. In general I'd say the tasks need to be defined, as I can give very many tasks to people right now that language models can solve that they can't, but language models to me aren't "AGI" in my opinion.

Its a definition, but not an effective one in the sense that we can test and recognize it. Can we list all cognitive tasks a human can do? To avoid testing a probably infinite list, we should instead understand what are the basic cognitive abilities of humans that compose all other cognitive abilities we have, if thats even possible. Like the equivalent of a turing machine, but for human cognition. The Turing machine is based on a finite list of mechanisms and it is considered as the ultimate computer (in the classical sense of computing, but with potentially infinite memory). But we know too little about whether the limits of the turing machine are also limits of human cognition.

That's kind of too broad, though. It's too generic of a description.

But OpenAI has received more than $13 billion in funding from Microsoft over the years, and that money has come with a strange contractual agreement that OpenAI would stop allowing Microsoft to use any new technology it develops after AGI is achieved

The real motivation is to not be beholden to Microsoft

Good observation. Could it be that Microsoft lowers profits by including unnecessary investments like acquisitions?

So it'd take a 100M users to sign up for the $200/mo plan. All it'd take is for the US government to issue vouchers for video generators to encourage everyone to become a YouTuber instead of being unemployed.

If they actually achieve AGI I don't understand what money would even mean anymore. It essentially is just a mechanism for getting people to do things they don't otherwise want to do, if the AI can do it just as well as the human, but for free other than the electricity costs, why the hell would you pay a human to do it?

It's like saving up money, in case of nuclear war. There are a few particular moments in history where the state of the world on the far side of the event is so different to the world on this side of the event that there's no point making any kind of plans based on today systems.

Because OpenAI is anything but open. And they make money selling the idea of AI without actually having AI.

Because they don’t have all the things they claim to claim to have, or it’s with significant caveats. These things are publicised to fuel the hype which attracts investor money. Pretty much the only way they can generate money, since running the business is unsustainable and the next gen hardware did not magically solve this problem.

They don't have AGI. AGI also won't happen for another laege amount of years to come

What they currently have is a bunch of very powerful statistical probability engines that can predict the next word or pixel. That's it.

AGI is a completely different beast to the current LLM flower leaves