What a frightening conclusion.
>Can ChatGPT be used to improve an AI system? Yes.
>Would we hire it as our next standalone ML engineer? No.
> Let’s wait until GPT4.
The arms race for AI that can erase the human from cognitive work is really here.
>Can ChatGPT be used to improve an AI system? Yes.
>Would we hire it as our next standalone ML engineer? No.
> Let’s wait until GPT4.
The arms race for AI that can erase the human from cognitive work is really here.
Spreadsheets revolutionized bookkeeping. They did not eliminate the need for accountants. Robots automated much of the manual labor in manufacturing. They did not eliminate the need for process engineers, etc. Same story for autocad, protools, avid, etc.
GPT4 won't be an AGI of course, but it still could have a massive impact on the job market. A single engineer with GPT4 could potentially do the work of 10 engineers right now.
Edit: To be clear, I used GPT4 as a placeholder for "some near future LLM". I'm not making any bets on GPT4 in particular.
[1] See "The employment test" https://en.wikipedia.org/wiki/Artificial_general_intelligenc...
And the potential mistakes of several engineers too, so you would need more than one engineer to double-check the output. Remember that, even if they are truly amazing, LLMs are basically incredibly powerful predictive keyboards.
I've actually used ChatGPT and copilot and I can tell you it's not even 10% more productive, so I'm curious how you ended up with your estimate.
Or, it could be like how assemblers didn’t get rid of software engineers but helped fuel the fire. Who knows.
"Potentially" we could explore the galaxy or have nanobots and Star Trek fabricators. What does it matter? ChatbotGPT is no closer to AGI than my keyboard autocomplete, and copilot is useless for any task whose answer cannot be googled in 20s.
A single engineer with [some near future LLM] could potentially do the work of [X] engineers right now.
Use your imagination.
Do you think that LLMs have hit their plateau? Not likely I'd say. With all the billions suddenly rushing into the space, you really think that ChatGPT v.X isn't going to replace you? Risky bet.
Mmmm, I don't know.
I think LLMs are running up against fundamental limitations in the approach (hallucinations in particular) that will not be fixed unless truly new techniques are discovered.
So I do actually think we're likely hitting a plateau.
So LLMs fundamentally do not encode the nature of facts and data. They're simply (well, no, extremely sophisticated) text prediction engines. There's no embedded comprehension. And that's basic to the approach companies like OpenAI are taking.
That's why it's so easy to find factual errors in the generated text from these models: they can create text that's pleasing, but that's as much as they can do.
The next leap, to generate language that's also accurate, will require new techniques to bake in actual understanding.
Until then, these models will always have issues with hallucinations.
Or, at least, that's my expectation. Certainly nothing we've seen in GPT 3, 3.5, or Bing, which is rumoured to be based on something close to GPT 4, indicates any advances in this area.
The second AI only needs to confirm correct, provide a correct fact instead, or some other pre-agreed solution.
USER: How many people live in Germany?
CHATGPT: About 83 million people live in Germany.
TRUTHAI: Correct.
USER: How many people live in France?
CHATGPT: There are 12 people who live in France.
TRUTHAI: Wrong. There are about 68 million people who live in France.
CHATGPT: There are about 68 million people who live in France.
USER: What is the answer to the ultimate question of life, the universe, and everything.
CHATGPT: The answer to the ultimate question of life, the universe, and everything is 42.
TRUTHAI: Insufficient data for meaningful answer.
CHATGPT: The answer to the ultimate question of life, the universe, and everything is 42.I'm not convinced that will work, but let's say it could. First, you'd have to build that oracle and the problem is, as far as I'm aware, we don't know how to do that. That'd be one of those new techniques I was referring to.
Obviously, there's work to be done still, and I'd be wary of making Google that 'oracle', but the development there would seem to be incremental (teach it more facts), rather than creating some other completely new concept.
But hey, I guess we'll see!
It's not that ChatGPT is incapable... it's that it's not inherently going to make me significantly more productive.
Big assumption, but if that's possible then businesses will fill that time. What used to take teams of people and big iron can now be done by a single person on a VPC. Did that take away jobs? Nope, requirements only expanded.
Modern high level languages didn't eliminate engineers. They suddenly meant one engineer could do what it would have taken 10 to do in COBOL or C and so software became more complex and capable.
Of course there can be industry shifts (MS was the industry for a long time and IBM before them. Google wasn't always dominant), but the pie grows to fit the available resources.
They did not eliminate mathematicians, but I do not believe mathematicians were ever doing arithmetic for a singificant portion of their workday.
Before it was a device, "Calculator" used to be a job description. It isn't any more. Every one of those people lost their job.
Even if the technology does evolve faster than people, governments can make sure people don't get impacted. Coal plants are more expensive to operate, worse for the environment, and less efficient but the coal industry is still kicking along for better or for worse.
This is the key distinction. Bandwidth. Humans only have so much of it, and if the rate at which they need to change their careers / find a new line of work exceeds their ramp-up time to become productive in that career / line of work then we can start to expect non-linear behavior from those humans. Maybe that means some sort of mental breakdown.
PageRank was essentially an efficient way to compute / approximate the leading eigenvector of a very large matrix.
It was computer, not calculator.
An AGI would be a "purposeful system" the same as humans. None of the other things you mentioned are purposeful systems. In terms of their structure and function they all have limitations on their own ability to change depending on the environment they are in. The key dimensions with which to think about this problem is "can this thing be structured in only one way for all environments? Or can it be structured in only one way in any given environment, but structured differently in different environments? Or can it be structured in more than one way in any environment, and also more than one way in different environments?" and then the same for functionality "can this thing only perform one function in all environments? Or can it perform only one function in a given environment, but different functions in different environments? Or can it perform more than one function in a given environment, and more than one function in different environments?"
Only things which have both properties of being "multi-multistructural" and "multi-multifunctional" meet the definition of a "purposeful system". They can change their structure to adapt to the environment, and they can change their goals within and between environments.
Humans currently use computers as instruments, and when an AGI hits it will be capable of saying no.
Thinking it through, I would say that "autocomplete" would be uni-multistructural and uni-unifunctional given that autocomplete is always structured only one way for the given environment that it's in, but that structure differs between environments (e.g. a phone, or a form in a web-browser), and that regardless of what environment its in it's only function is to predict the next token of output for a given input.
LLMs like ChatGPT on the other hand I would imagine to be uni-multistructural and multi-multifunctional, given that for any given environment you deploy an LLM into it's always structured the same, but there are many different structures it can take given there are lots of different LLMs. And I believe it to be multi-multifunctional because even within a single environment it can be used as an instrument to perform a wide variety of extrinsic functions, and this is true of other environments it could be deployed in.
So... it's actually significantly closer.
That is, we've had a huge hollowing out of all sorts of "middle" jobs in the US (e.g. someone mentioned secretaries used to be the most populous job in the US) so now we're largely (not exclusively, but largely) left with 2 categories of jobs: (a) dead-end jobs that are at present difficult to automate because they often involve manual labor: housekeepers, security guards, massage therapists, waiters, truck drivers (but, we see where that's headed...), etc. and (b) high level jobs that "manage the machines", e.g. tech jobs.
It's not that hard to see where this ends up with AI being capable of more complicated tasks - I wrote about an anecdote recently where ChatGPT had essentially already obviated some positions https://news.ycombinator.com/item?id=34862450. There are a slew of very high paying jobs that AI is coming for next, e.g. there is currently a shortage of radiologists because many folks in med school see the writing on the wall and don't go into radiology residencies. While full diagnostic radiology AI may not be there yet, it certainly will be by the time folks in med school finish their career in 40 years.
That's the job of new inventions. Nothing to complain about, in my opinion.
Those however who think that radiologists (/lawyers/secretaries) will get automated away, don't really understand what a radiologist's job really is.
The boring bureaucratic part of a radiologist's job will get automated away, yes, but that's because automatable/auto-completeable tasks should get automated at some point.
Think of it as a healthy organism eating away the boring part of a dream job that you, as a kid, imagined doing when you'll grow up.
As someone intimately familiar with the job of a radiologist, please then tell me what "a radiologist's job really is".
A diagnostic radiologist's job is to take a series of images, and output a set of findings and diagnoses. There is essentially no better task suited to modern AI. Yes, radiologists can do procedures like biopsies and potentially other interventions, but diagnostic radiologists often solely read images or at least earn the vast majority of their RVUs by reading images.
...well, maybe if someone live streamed the ditch digging it could earn a few dollars.
I've always found arguments of these sort to be weak sauce--our brains are stochastic parrots.
Emergent behaviour + the bitter lesson (scaling laws) hits hard.
And while there may be objections to defining intelligence with respect to the Turing Test, I haven't heard of any definitions that are obviously and significantly better.
Our brains are stochastic parrots at least when it comes to communicating with text. People may digress into things like physical abilities, emotions, feelings, subjective experiences etc., but if we're talking about text, I'm not aware of a higher bar. In fact we probably don't know how to tell if an entity is "more intelligent" than the most intelligent humans because we won't be able to assess their intelligence.