Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT: A Mental Model

xorvoid.com

Post reply on HN
Print view View original

71–80 of 99 posts

Re: ChatGPT: A Mental Model

#71

Post by allisdust »

pixl97 wrote: post #57
allisdust wrote: post #47

Earlier quoted context omitted.

Kind of I guess. If it is a single step: That is modify or generate text (could be code or anything) in a specific way, it works great even on obscure things. However if the problem is stated in a way that it has to think through derivative of it's solution: that is generate some code that generates some other code which behaves in a certain way, it fails miserably. I'm not sure why. The problem I stated in current t…

I'm assuming something like tree of thought needs used on problems like this. GPT 'mostly' thinks in a single step. Also, in general we attempt to make these models as economically efficient as possible at this point because of the extreme lack of excess computing power to run these things. You can't have it spending the next 30 minutes thinking in loops about the problem at hand.

Thanks for suggesting tree of thought. Will try the approach they mentioned in the paper.

Re: ChatGPT: A Mental Model

#72

Post by allisdust »

williamcotton wrote: post #53
allisdust wrote: post #44

Earlier quoted context omitted.

Aah, in case it wasn't clear the use case I'm trying to solve is exactly that: piping shell commands to and fro so that LLM has a bit of autonomy. I know that things like LangChain, AutoGPT exist but frankly they are really poorly thought out and seem to have become kitchen sinks too fast without solving anything properly.

https://github.com/williamcotton/autorails-alpha/pull/38

Thank you for the pointer. Very interesting approach. If you don't mind could you suggest some resources where I could learn more about your approach.

Re: ChatGPT: A Mental Model

#73

Post by yyyk »

LightBug1 wrote: post #13
jiggawatts wrote: post #2

Jiggawatts’ second rule: “Unless an opinion on LLM technology includes the specific phrase ‘GPT 4’, it can be dismissed.” The author tried older, thoroughly outdated models, and has decided to publicly state an opinion without bothering to check if it’s still valid or not. Ironically confirming that humans are just as susceptible to writing false statements as Chat AIs. Remember boys and girls: self driving cars don’…

//Remember boys and girls: self driving cars don’t need to be perfect, just better than humans. Fudamentally disagree. Self driving cars need to be effectively perfect (almost impossible) for me to consider them. I would rather be in a situation where the circumstances mean that there is a greater probability of me crashing, but under my control, rather than a "random" coding error or AI hallucination taking me and m…

Self driving cars can be effectively perfect - if we finally stop designing cars that cater to human drivers and stop trying to look like current cars. IMHO, if we finally accept that AI cars are different, we can achieve that level today. It starts with making use of AI's fast reactions and designing the car around that. Put the humans in the middle, and accept that the passengers have no role in driving, so you can pad them (and the front) so that crashes have much less effect. etc.

Re: ChatGPT: A Mental Model

#74

Post by williamcotton »

allisdust wrote: post #72
williamcotton wrote: post #53

Earlier quoted context omitted.

https://github.com/williamcotton/autorails-alpha/pull/38

Thank you for the pointer. Very interesting approach. If you don't mind could you suggest some resources where I could learn more about your approach.

Email your GitHub username to my HN username at gmail and I'll add you to the repo so you can take a look!

Re: ChatGPT: A Mental Model

#75

Post by LightBug1 »

mintaka5 wrote: post #33
LightBug1 wrote: post #13

Earlier quoted context omitted.

//Remember boys and girls: self driving cars don’t need to be perfect, just better than humans. Fudamentally disagree. Self driving cars need to be effectively perfect (almost impossible) for me to consider them. I would rather be in a situation where the circumstances mean that there is a greater probability of me crashing, but under my control, rather than a "random" coding error or AI hallucination taking me and m…

It's all about control, folks. I despise that you consider yourself the "savior" here because you saved your family from AI driving. Nope, you'd rather cast doubt on something than embrace it because of insignificant human ego. It matters to you and your precious family, but does it matter in the grand scheme of things? Huh?

Thanks for missing the core of my point. But your comment did give me a chuckle.

Your saviour has spoken.

Now. Kneel before your saviour.

I mean, why just stop at me and my family?

Are you kneeling yet?

Re: ChatGPT: A Mental Model

#76

Post by LightBug1 »

moffkalast wrote: post #31
IanCal wrote: post #23

Earlier quoted context omitted.

So you want to deliberately put your family in more danger just so that it'll be your fault if they get hurt?

https://en.wikipedia.org/wiki/Illusion_of_control It's a cognitive bias in all of us, including the lawmakers approving the use of self driving cars.

I disagree, I'm aware of that fallacy and that's not quite what I'm getting at.

I've driven cars for 20 years and my driving has (imo) improved over that time.

I'm at a level where I don't see a reason for me to get into any serious accident by my hand. It's just not going to happen * fingers crossed *.

I know my driving style. I know I'm a safe driver.

Now, why would I give that security over to "FSD", which is clearly a decade (if that) away from being user-ready?

Don't get me wrong, as said, certain automation is cool ... stop/start in heavy traffic, lane assist, cruise control, crash avoidance even ... but beyond that? I'm A-ok ... don't need to introduce the risk from half-baked code (no offense, but that's true at this stage) or AI where we don't really yet know what the output will be (despite being impressive "most" of the time).

Now, I'm speaking about me. You can do what you like. And if you're willing to hand over the reigns of your life to some beta programme, be my guest. Just don't drive in the opposite direction to me for, say, another 10 years. Thanks.

Re: ChatGPT: A Mental Model

#77

Post by skyechurch »

spion wrote: post #63
skyechurch wrote: post #59

>it doesn’t have any underlying model of the world Citation needed. ChatGPT doesn't have an explicit underlying model of the world separate from its language model, but it is unclear that this is necessary. It would not be an original philosophical position to say that language, properly understood, is definitionally a model of the world - otherwise it would be incapable of expressing anything true or false about the…

Citations needed indeed - ones with formal tests / experiments being carried out and constructed that would show the problems. Speaking of those, my best example of ChatGPT not having a good model of the world are citations. ChatGPT clearly has knowledge about how citations work, based on what it would tell you if you ask it. Yet it repeatedly invents non-existant ones: https://simonwillison.net/2023/May/27/lawyer-ch…

>Speaking of those, my best example of ChatGPT not having a good model of the world are citations.

Absolutely. ChatGPT is not sentient, not in any conventional sense at least, and the errors it confidently makes are not the sorts of errors a human would make. Its model of the world is based entirely on language, it doesn't have all sorts of capabilities that humans (and animals generally) clearly do have. It's definitely not a person, any more than a walking robot is a person, like the robot it's just reproducing some aspect of what living things do. My only point is that the significance of this achievement is not understood right now, not by anyone afaict, so confident statements that it is/isn't really "thinking" in some way are all empty. One could - if one wanted to be a smartass - say we lack a underlying model for what AIs and human brains are really doing, and then term all these sorts of opinions "hallucinations". I am hopeful that deeper investigations of this will lead to progress on some very deep and long-standing philosophical problems.

Re: ChatGPT: A Mental Model

#78

Post by IanCal »

LightBug1 wrote: post #76
moffkalast wrote: post #31

Earlier quoted context omitted.

https://en.wikipedia.org/wiki/Illusion_of_control It's a cognitive bias in all of us, including the lawmakers approving the use of self driving cars.

I disagree, I'm aware of that fallacy and that's not quite what I'm getting at. I've driven cars for 20 years and my driving has (imo) improved over that time. I'm at a level where I don't see a reason for me to get into any serious accident by my hand. It's just not going to happen * fingers crossed *. I know my driving style. I know I'm a safe driver. Now, why would I give that security over to "FSD", which is clea…

So would you do it if it was a better driver than you? Your earlier comment said you wouldn't even if it made a crash less likely. I'm not really sure how to parse that given this followup.

Re: ChatGPT: A Mental Model

#79

Post by mft_ »

pixl97 wrote: post #54
mft_ wrote: post #34

Earlier quoted context omitted.

That's not quite the issue I'm raising. It's not about being able to communicate better with existing robots - it's where (as yet) there are no robots suitable to do the job. There are plenty of tasks which are simple, tedious and repetitive - and yet are resistant (currently) to automation. An example is sorting mixed plastic waste into categories according to the type of plastic. This is comparatively trivial for a…

Let's imagine a world where most jobs that cannot be automated are low end, low skill, low pay jobs... what does this world look like economically? In my eyes this is a world where corporations and the extremely wealthy suck up all the economic benefits and we're left with massive wealth disparity. Assets keep going up in price, but there is no means of monetary velocity to the bottom earners.

I don't disagree (notwithstanding the extent to which we're already in a "world where corporations and the extremely wealthy suck up all the economic benefits and we're left with massive wealth disparity").

My point is much more narrow (and simple): that there is a subset of low-end jobs which are currently unautomatable due to their nature, and this will likely not change via the GPTs. This may (tending to will, given sufficient time) change via other technological advancements.

Re: ChatGPT: A Mental Model

#80

Post by gmaster1440 »

skyechurch wrote: post #77
spion wrote: post #63

Earlier quoted context omitted.

Citations needed indeed - ones with formal tests / experiments being carried out and constructed that would show the problems. Speaking of those, my best example of ChatGPT not having a good model of the world are citations. ChatGPT clearly has knowledge about how citations work, based on what it would tell you if you ask it. Yet it repeatedly invents non-existant ones: https://simonwillison.net/2023/May/27/lawyer-ch…

>Speaking of those, my best example of ChatGPT not having a good model of the world are citations. Absolutely. ChatGPT is not sentient, not in any conventional sense at least, and the errors it confidently makes are not the sorts of errors a human would make. Its model of the world is based entirely on language, it doesn't have all sorts of capabilities that humans (and animals generally) clearly do have. It's defini…

I wrote a short piece on this almost 3 years ago shortly after GPT-3 came out, I share a lot of your intuitions here: https://www.markfayngersh.com/posts/the-thinking-placebo
Post reply on HN