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

CheatGPT

blog.humphd.org

Post reply on HN
Print view View original

361–370 of 544 posts

Re: CheatGPT

#361

Post by jesterman »

JohnFen wrote: post #331
iameli wrote: post #326

Earlier quoted context omitted.

I can't claim to understand everything my brain is doing, but accepting input and filtering it through a bunch of neuron chains to result in some kind of output sounds like "statistical analysis" to me. You seem convinced that ChatGPT will never have "actual intelligence" — care to make a prediction about something that LLMs will never accomplish? We know they can write code, write essays, generate artwork, and play…

An LLM will never be able to produce something that cannot be statistically derived from its training data. So... creating a new language, maybe?

I see what you are going with here for it not being able to come up with original things. But I think that falls apart when you realize almost nothing humans do is original, everything is just building on other things.

Re: CheatGPT

#362

Post by dinkumthinkum »

ramesh31 wrote: post #27
jasmer wrote: post #17

Earlier quoted context omitted.

??? By this reasonning nobody should ever learn anything, because it's all 'trivially doable' by machine. Like 'addition' and 'subtraction'. So let's gaslight those dumb teachers by saying they should make up 'better' homework assignments?

>By this reasonning nobody should ever learn anything, because it's all 'trivially doable' by machine. >Like 'addition' and 'subtraction'. A better analogy would be low level coding. I don't know (or care) how my processor calculates `var f = 3+2` at the register level. And being able to ignore that allows me to focus on higher level concerns.

If you don’t know that then you really have a real lack of knowledge of computing. I don’t mean that as an attack or anything but I don’t think it is a badge of honor or anything. You could just as easily say the person typing a Word document doesn’t know what RAM is so we can just stop teaching that foolishness so people can focus on the “complex” things.

One could also argue, and many have successfully, that this type of thinking is why software is so much slower than in the 80s and 90s.

Re: CheatGPT

#363

Post by jefftk »

asdff wrote: post #224
jefftk wrote: post #206

Earlier quoted context omitted.

And then someone in the dorm makes a keystroke injector, and everyone goes back to typing their code on their own computer. Ex: https://null-byte.wonderhowto.com/how-to/make-your-own-bad-u...

IT dept can disable loading volumes that aren't the university shared drive for assignment turn in. They can also supply laptops vs desktops with wired keyboards.

I'm proposing a device that pretends to be a keyboard, and mimics typing in the code

Re: CheatGPT

#364

Post by h9n »

> the current funding model of post-secondary institutions, which does not prioritize the ratio of faculty-to-students necessary for ever more personalized or real-time assessment methods.

Get ChatGPT to do the assessments.

Re: CheatGPT

#365

Post by test6554 »

stillsleepy wrote: post #91
novok wrote: post #53

The failure mode of things like ChatGPT is it can make wrong answers confidently, subtly, and if you don't have the skill to audit what is wrong with the answer, then it can be fairly catastrophic. So instead of making questions generative, you make them audits / debugging type ones. Use ChatGPT to generate a result after several iterations that is wrong and then ask them what is wrong with the result. Since ChatGPT…

the other week i gave chatgpt a simple multiplication problem that it got wrong. very simple problem like 86 * 0.0007 or something. but ive been working with chatgpt for 4-5 weeks now and that wrong answer doesnt make up for all the "good answers" that are usually not perfect. like one day i needed to COALESCE in mysql. i didnt know that, but chatgpt did. theres a few times i would have written a function the complic…

It contains 3 or 4 trips to stack overflow in its one answer. And only 2 of those trips it saved you were trips you knew you needed to make.

Re: CheatGPT

#366

Post by javierluraschi »

Gone through all the big-tech interviews, previously worked at Microsoft and a few more. I'd say that the only interview question I think survives here is what we've been doing at our startup: "For this role, here is a real four hour problem for you to work on, let us know when you want to start and we will send you the problem, send it back four hours later and then we will schedule some time to chat about it". If someone uses ChatGPT and solves it better than other candidates, that's great, good for them Don't think it's possible to solve it entirely with ChatGPT, but I could see some good candidates getting pointers to solve a 10%-30% of the problem to make them more efficient, before ChatGPT people could Google anyways and honestly I would expect they do.

I think a similar approach should apply to schools. Here is your math homework, solve it whichever way you want but then we will discuss it. I guess this would be the oral approach from the post but minimizing the time it takes to do the oral review. If your homework assignment has 20 questions and you discuss one with each student, you'll get a pretty good overview if they know what they are doing. If they want to ask ChatGPT for replies during this oral test, go for it, but they still get the same amount of time to discuss the question, is going to be really hard to get this done realtime. Also, I'm not sure ChatGPT really understand what it's doing to the point where an expert can prove it in limited time.

Re: CheatGPT

#367

Post by dcow »

Jtsummers wrote: post #351
dcow wrote: post #330

Earlier quoted context omitted.

Which is odd because in every other language that uses let (lisp, scheme, swift, rust, scala/kotlin val, haskell, etc.), let bindings are const and let is synonymous with const.

Let bindings in Lisp are not const. You can use `setf` (among others) to mutate the variable. For instance, this works just fine in Lisp: (let ((x 1)) (print x) ;; => 1 (incf x) (print x)) ;; => 2 Scheme also allows let bindings to be mutated, but using `set!`.

I assumed scheme and lisp were the same here semantically. Bad assumption on my part. My experience is primarily with scheme.

Similar Rust and Swift allow let bindings to be shadowed but you need to re-declare your intent. You can't just mutate the binding on a whim.

Re: CheatGPT

#368

Post by grugagag »

krembanan wrote: post #274
throw310822 wrote: post #209

I don't understand how most of the comments here seem to be along the lines of "these interview questions are useless now" or "we need to rethink education, it hasn't kept up". These all seem absurdly myopic to me. What we're seeing is the first instance, still very limited and imperfect, of AGI. This is not going to make some interview questions obsolete, or give students more tools to cheat with their homework. It…

Software development isn't really about just acquiring and memorising knowledge to later spit out. You need reasoning, logic and creativity. That AGI can develop complex new software (not just some code that has been scraped of the internet years ago) in 10 years is something I doubt.

We don’t have AGI as of now but it could spark anytime and its acceleration could be extremely fast. It could almost spark and yet never really get there, just get closer and closer and quite never hit the mark. But this is not something that will simply stop a massive disruption in most professions and livelihoods, LLMs could do that easily

Re: CheatGPT

#369

Post by modeless »

abernard1 wrote: post #227
modeless wrote: post #51

Earlier quoted context omitted.

> What humans being to the table over ChatGPT is Statements like these are premature. ChatGPT is three months old! This is a rapidly advancing field. The capabilities of these models are very likely to be radically different five years from now. Any conclusions drawn now about what value is uniquely human and out of reach for AI may be proven wrong quickly.

> The capabilities of these models are very likely to be radically different five years from now. This is an article of faith. Specifically, it believes that at some point in the future the current paradigm will result in qualitatively different behaviors than the mimicry these systems (all GPT variants, "Attention is All You Need") currently perform. Much ado has been made of the previous Symbolic AI researchers "mo…

> connectionist trickery

I don't know, man, you kind of come off as having a chip on your shoulder about this. I'm not predicting AGI specifically here, and I'm not making any argument about symbolic vs connectionist AI at all. Maybe the model of the future is half symbolic! I'm just saying that asserting that you know exactly which things AI models aren't going to be able to do is pretty foolish at this point.

Re: CheatGPT

#370

Post by jstanley »

JohnFen wrote: post #333
zeckalpha wrote: post #329

Earlier quoted context omitted.

Can you point to where the thinking happens in a human?

Nope. But I don't have to do that to understand that LLMs do not assess truth or accuracy of anything.

But you don't know that humans don't reason by stringing words together and seeing how statistically likely they seem.

Related to this topic, see "Babble and Prune": https://www.lesswrong.com/s/pC6DYFLPMTCbEwH8W

Post reply on HN