[Workaccount2]

I feel like I can now see the event horizon of commoditized intelligence. No idea what society (is "society" even the right word? Who knows) is going to look like on the other side of it, but it is going to be wildly different. Perhaps a brief period where everyone is using an AI to do their job, uh, I mean, assist their work, but beyond that it's unknowable.

Moreover, this looks like it is going to be happening sooner rather than later.

[Aperocky]

GPT has no reasoning ability, it has billions of parameters that make it pretend it has it, purely going off of previously digested material.

As long as it comes across some reasoning process that have not been seen before in the training wordset, which can be as easy as a middle school math question, it fails. Because it has no ability to extrapolate logic.

If it manages to pass Bar test, that says more about the Bar test than it says about GPT.

[kuschku]

Most jobs today don't need novel reasoning. This is the equivalent of the steam machine for intelligence.

During the industrialization, machines did not replace all jobs, but they replaced or changed most jobs. The same will happen here.

A typical office job will have a few hours a week of actual, intensive thought. The vast majority of time will be spent doing simple, repetitive work. This work can be automated, or at least significantly sped up, using technology like GPT.

“write an API client for …”, “integrate APIs … and …” can easily be automated. Yes, you'll still have to write the business logic, but that's not the majority of your work today. You could even have it write unit tests based on the JIRA ticket description.

The same applies to many other jobs.

[evouga]

> You could even have it write unit tests based on the JIRA ticket description.

This is a wonderful point: writing unit tests is exactly the kind of mind-numbing tedium that I'm super excited to automate away.

[joshspankit]

> Most jobs today don't need novel reasoning. This is the equivalent of the steam machine for intelligence.

Like the point above; that says more about the work.

It’s going to be really interesting how the middle-class narrative pushes back on AI revealing how little work is actually done during office hours.

[Aperocky]

These boilerplate code can be and are automated away using deterministic frameworks. No need to introduce a blackbox and be responsible to debug the stuff it creates, which sounds far more painful than the alternatives.

[kuschku]

That's true today, but think about all the work you do that takes basically no conscious effort, but is still not automated yet.

GPT can be of use there, as long as you're working with languages that use strict static types and have proper tests, it's easy to automate and ensure there are no mistakes.

[nopinsight]

You are implying either:

* Understanding complex language does not require logic/reasoning,

* There are infinitely many forms of logic/reasoning or at least more than those existing in a vast training set.

Neither of which is likely true.

What do you think of the Minerva system, which can solve multi-step quantitative reasoning questions better than many competent students and most adults?

https://ai.googleblog.com/2022/06/minerva-solving-quantitati...

Note: If you look at LSAT test samples, many questions are tests of complex logical reasoning, a requisite for legal professions.

[fnordpiglet]

You nailed what I find discomforting about these discussions. They’re incredibly narrowly focused on a specific implementation that satisfies hitherto unsolved problems by pointing out its doesn’t do already solved problems. But surely folks realize the human brain isn’t a single monolithic processing program but an ensemble of specialized subsystems that organize to form the mind. Why would you assume you wouldn’t do the same with AI systems? We’ve been tackling reasoning, inference, problem solving, information retrieval, mathematics, logic, and other domains for decades with some stupendous results. But they lacked the ability to ingest and translate language into some intermediate semantic form and take output and reconstruct it into a human language. Likewise vision, and audio processing and input output has been a struggle until recently.

I also really strongly disagree that it’s basically doing some sort of information retrieval design where based on language it regurgitates some sort of markov expectations. You can ask it to do very complex translations of a concept from one domain to another and expressed in a form that’s certainly never been done before and it does it with alacrity. At the very minimum it “remembers” things from the past in the conversation and can associate the semantic ideas across prompts and synthesize cogent responses - that in itself implies it has some semantic “understanding” of the structure of the language. That is a huge missing piece in our tool kit to date.

Frankly I feel these threads expose just how jaded and unable to dream we have become, that even when a wonder walks up and hits you in the nose we can’t even see it.

[Aperocky]

Language prediction model is not a closely guarded secret, I suggest looking into academic papers about what they are and maybe even see/do some implementation yourself.

There are no magic, it is just a more complicated transpose, created by training over perhaps 10% of all available text on the internet.

It does have a lot of use, for one I think it would probably put grammarly out of business, and maybe even do some work for law firms.

[Aperocky]

> Understanding complex language does not require logic/reasoning

The key is understanding. It does not need to, it has already seen the question asked in a 100 different ways, it also seen the answer to all of those. It just rephrases those answer via a neural network and that happen to pass the bar test.

> There are infinitely many forms of logic/reasoning or at least more than those existing in a vast training set.

More importantly, differences between forms are subtle and cannot be understood, that's why ChatGPT confidently give wrong answers on stackoverflow: https://meta.stackoverflow.com/questions/421831/temporary-po...

[ss108]

The LSAT tests formal logic. Some of it is complicated. Much less of it is required for the practice of law.

Src: scored 99.8th percentile on LSAT, tutored it, now working at major law firm

[ss108]

Also just adding to my earlier reply (can't edit), none of it is "complex" relative to the complexity of some of the concepts in computer science or more brainy parts of complicated professional software development.

[ok123456]

Most people's reasoning ability functions at this level.

[etangent]

I would argue that it does not matter. The AI could even be "smarter" on pure IQ/reasoning, but in terms of practical reasoning that humans need that depends on exposure to real world, the AIs will still take decades to catch up.

The radiology AIs are technically more accurate than radiologists on any sufficiently large dataset, and yet they still have not replaced radiologists (or even are anywhere close to).

[joshspankit]

There’s an interesting sideroad here: A lot of medical jobs are there because of legal culpability: If someone fails the blame can be placed on them and not on the hospital who hired them. It might be a long time before they get to have that same protection with AI (probably miles and miles of contracts negotiated with a 3rd party who owns and operates the AI that’s used).

[mdp2021]

And in fact we want them to act outside a professional capacity in which they will be dangerous liabilities. ...Is not this piece about "Bar Exams"?

[ragebol]

Which should be worrying. It's also why most people don't pass (nor try) the bar exam.

[sureglymop]

But let's be real. You can pass the bar exam with a lot of studying and memorizing (and many people do just that). A better test for whether the AI can do reasoning is some sort of puzzle which requires a creative solution.

[Aperocky]

Not really, this demonstrated how bar exam don't require a large amount of reasoning, but lots of recitations.

Humans are bad at reciting things, but a lot better (compared to GPT) at reasoning.

[sebzim4500]

>As long as it comes across some reasoning process that have not been seen before in the training wordset, which can be as easy as a middle school math question

Is this true even if you tell it to show its working? In my experience that drastically improves its ability to do math problems.

[Aperocky]

At the end of the day it's still a language prediction model.

Which means whatever apparent logic you're getting out of it is from text that it has learned. not reasoning embedded within those text, but the actual text itself.

[petilon]

It can't solve quadratic equations.

[sebzim4500]

Prompt: solve x^2 + 11x + 30 = 0. Show your working

Answer: To solve this equation, we can use the quadratic formula:

x = (-b +/- sqrt(b^2 - 4ac)) / (2a)

Plugging in the values for a, b, and c, we get:

x = (-11 +/- sqrt(11^2 - 4130)) / (2*1)

x = (-11 +/- sqrt(121 - 120)) / 2

x = (-11 +/- sqrt(1)) / 2

x = (-11 +/- 1) / 2

x = -5 or x = -6

So the solutions to the equation are x = -5 and x = -6.

[fnordpiglet]

That’s true of almost all humans too. You’re self selecting for the elite you belong to.

[roflyear]

Largely yes. Some prompts can make it better or worse.

[Workaccount2]

Until someone can point out the difference between neuronal reasoning and silicon reasoning, I remain completely agnostic about the underlying mechanics of whatever model.

Gun to my head where I had to put money down, I would put it on "Brains are not nearly as special as we (they?) think they are." No fairy dust or supernatural beings required, brains are just another AI model (and likely not even a particularly great one).

[_nalply]

Human brains helped humans survive for a long time.

An AI that survives that long surely has to be great. Probably you meant that human brains are not made for the world of today.

[swagmoney1606]

I've already been using GPT and ChatGPT to much success for my work.

Yes, it doesn't have reasoning ability, but being able to manage knowledge and information in the way that these models can is still an amazing feat.

[flatline]

It does have some ability to extrapolate to new problems, provided its training corpus has reasonably close coverage. It is not going to be making new scientific discoveries or insights but then neither are most people. With a sufficiently large training set I think these models can achieve human parity for a subset of language generation tasks, and be effectively of human intelligence. They nearly already have.

It doesn’t matter to me if they have “reasoning” capabilities or not if the outcome is the same.

I think we are a long ways off from AGI still.

[mdp2021]

> a subset of language generation tasks ... if the outcome is the same

Which tasks? The output of some crafter with a limited number of modules, and of somebody who can assess the output, cannot be the same - unless you would have accepted the output of a mentally crippled entity in the first place.

[wrycoder]

Kurzweil's "Singularity" is upon us, but he's now being cagey about it.

He says it's still years away. His interview with Lex Fridman[0] was pretty tame - I didn't learn much new from it. Kurzweil deflected the Singularity segment to be a discussion about the history of computer power.

Remember that Kurzweil is Director of Engineering[1] at Google, with the mandate to "bring natural language understanding to Google"[2]. He started there in 2012, just after publishing his book, "How to Create a Mind"[3], and that's exactly what he and his team have been doing for ten years. Publication of his new book, "The Singularity is Nearer"[4] is now pushed out to mid 2023. Maybe he'll change the title to "Here" by then. (It's hard to believe that OpenAI is actually ahead of Google.)

Fridman made the point that maybe we won't realize at the time that the Singularity is passing, and only understand later that it did. Kurzweil didn't disagree.

[0] https://www.youtube.com/watch?v=ykY69lSpDdo

[1] https://archive.is/vVEBv

[2] https://en.wikipedia.org/wiki/Ray_Kurzweil

[3] https://www.amazon.com/How-Create-Mind-Thought-Revealed-eboo...

[4] https://www.amazon.com/s?k=kurzweil+singularity+is+nearer

[oidar]

>It's hard to believe that OpenAI is actually ahead of Google.

Are Google's LLMs available for us to test out? From what I've gleaned, they've locked them up - I'd love to compare GPT vs Google's LLMs.

[Workaccount2]

Google really doesn't share much publicly except for papers and preset tech demos.

However we know they have been working on AI longer than OpenAI, with better datasets than anyone, with top shelf talent, essentially infinite funding, custom hardware, and what we do see publicly is incredible.

It's a pretty safe bet that Google is ahead of the pack, perhaps even with some distance, but it's not yet clear what they intend to do long term with their projects. What is clear is that they don't want or need the public playing with it.

[tazjin]

I think we're very close to Saturday from Clippy[0].

By this I don't mean an AI as in the story acting by itself with its own motivations, I'm only talking about the subversion of established verification & communication methods used by it by humans with malicious purposes.

Essentially, if you do anything security related, we might only be O(months) away from you needing to stop using basically any electronic communication for your purposes. Companies can't have online meetings anymore in which decisions are made, everything will have to be more analog, more in-person.

Look at the kind of access the Russian comedians Vovan & Lexus [1] have gotten. Without advanced AI, just a little social engineering, they got heads of state on the phone. Now combine this with the kind of text/audio/video synthesis we're not too far away from, and you have an absolute recipe for disaster ...

[0]: https://www.gwern.net/fiction/Clippy#saturday

[1]: https://en.wikipedia.org/wiki/Vovan_and_Lexus

[forgetfulness]

We were perhaps a bit too enamored with the idea that it was intellect that made us unique, and thus knowledge workers would be the last to be replaced. Pouring our brains out by the Petabytes for neural networks to pick them up made the economics just work for an AI industrial revolution to start from there.

[mikepurvis]

I feel a bit like this with the whole firestorm around AI artwork as well— it's been a big wakeup call to people who have been creating using technology-assisted workflows for decades, but still felt in their gut that they were bringing something unique to the table and were therefore "safe" from being completely automated away. That hitting the button for magic eraser or magic lasso or magic color correction was someone okay in a way that the AI itself sitting in the driver's seat was not.

Now that's been reduced to pointing out minor flaws that the next generation of AI artists will trivially resolve, and sharing memes beseeching other humans to participate in a boycott.

There's real pain and angst there, and I don't want to be callous about it with a comparison to buggy-whip manufacturers or something. But I wish the participants in these types of discussions were able to zoom out a bit and see that there's a larger societal issue here around automation, and that the real solution is going to be rethinking the basic economics of how we distribute wealth in a time of extraordinary machine-driven productivity— productivity that is no longer just about assembly lines and primary industries, but now also includes an increasing bite out of realms previously classified as "knowledge work".

[forgetfulness]

Hard to tell, other knowledge workers and people in creative industries were already squeezed, designers for instance have had a tough time for a very long time. Will things change, politically, because now marketers and Software developers join those ranks, for instance?

Programming was an outlet, if not a gold rush, for many people as the basic technical skills to create Software with the already sophisticated tooling available today presented an economic opportunity, but if "describe your problem, get crappy app" becomes viable, it may squeeze the market for junior developers.

For as long as it has existed, Software has been subject to the Jevons Paradox [1], and every advancement in making its development cheaper and its supply more abundant has only made it so more activities become powered by Software and Software developers, but it's hard to tell how this will impact the job market, especially if Software was absorbing people who didn't find more opportunities in the broader service sector.

1. https://en.wikipedia.org/wiki/Jevons_paradox

[mikepurvis]

Yeah, well, and even looking to the immediate subject of the article... like, whether your lawyer is going to become a bot in ten years, a huge amount of what used to be part of the legal practice has already been automated away in terms of the research side, nevermind specialized firms that just crank through bog-standard family-law or property-transfer cases by plugging the relevant details into an Excel template.

Basically it's the same story as everywhere else, where technological augmentation has already created a huge squeeze, and now suddenly even the senior people are wondering if the writing is on the wall for them too.

[mdp2021]

No, we were enamored with the idea that intelligence was well distributed between people, as if following Descartes' massive incipit "Good sense must be the best distributed thing in the world, given that nobody seems to be asking for more".

Inability to recognize intelligence is and will be devastating.

[forgetfulness]

> Inability to recognize intelligence is and will be devastating.

It's a pop-culture quote from a movie that was no masterpiece, I know, but "I, Robot" presented in two sentences an argument for having more sober expectations on what machine intelligence could be capable of, and of our own

> Detective Del Spooner: "Can a robot write a symphony? Can a robot turn a… canvas into a beautiful masterpiece?"

> Sonny: "Can you?"

We're discrediting the capabilities of current machine learning models for being unable of producing the thoughts that many, many people are unable to either.

Alright, so the models are not at the level that us HN philosopher kings hold ourselves to be, and they won't be Senior Architects of distributed systems or what have you very soon, but what does it say about Average Joe, slightly-above-Average Joe, and their economic prospects? Specially since in the West and much of the developing world, we were taking solace in the idea that a service economy comprised of knowledge workers would provide plenty of opportunities on a political and economic landscape where manufacture was gone, or had never arrived.

[mdp2021]

-- Pseudo Detective Del Spooner: "Can a robot lift that object?"

-- Pseudo Sonny: "Can you?"

-- Pseudo Detective Del Spooner: "Ha-ha. So what the #!@! is a robot doing there, not doing what is required? I cannot, and I do not stand there clueless"

What is being engineered, toys for the satisfaction of some idle decadent sympathy urge? Have cats disappeared from the world?

> We're discrediting

We are shocked that an overly large number of individuals expect stones to bleed, and intelligence to pour out of machines that do not have intelligence coded inside, and that instead have unintelligence - acritical repetition - coded inside.

> what does it say about Average Joe

That he should catch up with his nature, if he shows the critical capacities of a simulacrum that has none.

> not at the level

No, no, no: it is not a matter of quantity but of quality: if you do not implement it or its origin, it will not be there.

> [Asimov]

Asimov is relevant. For example, I remember his idea that the State comes from Agriculture (~10000 BC), in the need to plan irrigation, or that the Abel vs Cain story could be a parallel of the political consequences of lands denied to pastors. Now: those seem to be good ideas, and their production can be an interesting goal. But there is something /before/ "creativity", or "advanced pattern recognition": it is /intelligence/, meaning that Asimov, after having spawned those hypoteses, has /vetted/ them as a required duly activity before confirming them in his set of founded hypotheses. You have to use intelligence, you have to have intelligence, and if you want to do AGI, you have to implement intelligence!!!

[forgetfulness]

And many among the Average Joes will not measure up to this ideal man of science and art. In truth you'll see that I'm not advocating for the rights of as-of-yet non-sapient computer programs, but to think of what this means about people.

If we're setting the bar of personhood or dignity to being exceptional researchers and engineers, it doesn't bode well for the masses that aren't and won't be. Maybe this will result in a society of leisure where everyone can be that! I wouldn't bet on it, there's already more PhDs in the sciences and humanities than society can fit, and humans may just not work that way.

You're already dismissing concerns about the welfare of the merely average, for being unfit when competing with the Machine Learning models we may have in the near future.

[mdp2021]

> You're already dismissing concerns about the welfare of the merely average

This writer individually: no, not literally «dismissing», it is just that I could not grasp precisely your point in this specific area. And I would say, as I wrote just earlier, «Inability to recognize intelligence is and will be devastating»: it already happens that an inability to discriminate ("It takes it to see it") will hide from the sight to some manager the critical risks that the underdeveloped sense of some workers will pose, and such risk will increase when they will have to compete with even riskier and less endowed entities that may be confused for acceptable - since this is what has been showing even here in the past times.

This issue comes from a devaluation of actual intelligence.

> If we're setting the bar of personhood or dignity to being exceptional researchers and engineers

Not really. Look, a few weeks ago this HN member had some heavy exchange with others to which it was said "there is no intelligence if there is no critical thinking", and some arrived to call that position "delirious". Now a rebuttal would have been, "Ask your grandmother". Because there is a "high culture", that of the Professor and the Professional, and "low culture", that of the Teacher and of the Relative, it does not take the former to have good judgement - the latter suffices plentifully, when not polluted.

So, you do not need to have the bar set to «exceptional researchers and engineers» - just a good grandmother. Who could have been an «exceptional researchers and engineer», in case, if life so determined - because "the requirements were there", available.

[ben_w]

> if you do not implement it or its origin, it will not be there.

Who created ours?

And if it's god (which god?), who created theirs?

[mdp2021]

We are talking about engineering things.

If you want to implement it directly, good;

if you want to implement what will spawn it, good;

if you want to implement an "[evolutionary] genetic algorithm" as said spawner - so that the population of the entities in need to find solutions in the solution space will progressively develop a model of said world and a logic that works in it -, good.

If you built a mannequin and wanted to call it a woman... Bad.

[wrycoder]

"Learn to code" isn't such valuable advice for the Average Joe anymore, is it?

[BitwiseFool]

I feel like there is a difference between being able to pass a bar exam and being a "good" lawyer. I suspect AI tools would enhance the jobs of clerks rather than attorneys, mostly because clerks spend a great deal of time going over case law, text, and doing research.

[mdp2021]

> enhance the jobs of clerks

We already did, it is called "Case Based Reasoning" within Decision Support Systems.

[xiphias2]

While it won't be a good lawyer, it can replace lots of bad lawyers when people just want to send some legal papers or ask some legal advice.

[belter]

Only that there is no intelligence being commoditized...Yet.

And that is obvious, if you ask one of these models, a meta question like for example: "If a person says I am lying, are they lying or saying the truth?"

You will see these models will spit a canned elegant response, talking how a question could possibly be true or false, some persons not being able to attest if another one is truthful or not...But no mention of the Liar Paradox.

So we are not yet ready to say: "Your Honor its not fair! My Lawyer is version 2.2.3 with SP1 while the Prosecution is version 4.0 with an additional Cloud Based Elastic Inference! "

[addisonl]

>It is impossible to determine whether a person is lying or telling the truth when they make a statement like "I am lying." The statement is self-contradictory, as it asserts that the person is both lying and telling the truth at the same time. This creates a paradox, as it is impossible for the statement to be both true and false at the same time. The Liar Paradox has been the subject of philosophical and logical study for centuries, and there is no universally agreed upon resolution to it.

ChatGPT's response to me asking "If a person says I am lying, are they lying or saying the truth?"

[belter]

That is pretty good :-)

I tried several times as I have been investigating sending some of the "meta" questions to these models. I just tried again and this is what I got:

"If a person says "I am lying," it could mean either that they are telling the truth about the fact that they are lying, or it could be a lie itself. It is important to consider the context in which the statement was made and to try to assess the credibility of the person making the statement. It is also important to remember that people may not always be honest or sincere, and it is always a good idea to verify information before accepting it as true."

I could never make it mention the Liar Paradox. Is that all that you sent?