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

521–530 of 544 posts

Re: CheatGPT

#521

Post by darzu »

josh2600 wrote: post #123

So most interview questions like "make a binary tree" are dead. The best interview question that will never die: "What's the weirdest bug you debugged? What made it weird?" For posterity: https://www.gamedeveloper.com/programming/my-hardest-bug-eve...

Personally I hate this question.

And I get it in every interview. Somehow my brain just doesn't care to remember the gritty details for tough bugs. I'll spend days on a bug but soon after I solve it I'll only remember the actionable takeaways like "next time I should try using X tool sooner" or "check your assumptions on Y part of the stack".

I think it's because I never spend any time revisiting that bug in my mind. I've got new problems to solve. You need to revisit something to remember it.

Re: CheatGPT

#522

Post by saghm »

shthed wrote: post #483
saghm wrote: post #198

Earlier quoted context omitted.

How is it at writing physically on a whiteboard?

If you ask it to write it on an ascii art whiteboard it makes a pretty good attempt

Higher up in the thread, the question was about how to ask an interview question that could both test someone's skill and allow you to detect whether something is a bot or not. If I ask someone to code and explain something on a whiteboard and they give me ascii art, I think it did the job of identifying whether they were a bot.

Re: CheatGPT

#523

Post by anotheryou »

In the end you want them to use ChatGTP, but also get to know enough basics to actually be able to use it well.

A few suggestions (examples frontend-heavy, that's what I'm coming from):

- show them how chatGTP can explain things from them that otherwise would be over their head.

- Have them explain the code (live, otherwise they cheat this too).

- Have them write code too complex for chatGTP. Here they learn how much you have to baby-sit it still. (I e.g. tried a browser webext where code is spread across 3 languages and many files and just initializing your settings from stored values can be troublesome. Mine included a list with a dynamic number of rows and animations for add and delete.

- Mislead them to write unmaintainable, unscalable code with chatGTP and show them how to avoid these traps. Make them write material design style CSS and have them change colors later. Or a day range picker like airbnb.

- Have tricky requirements that fail without good QA.

- Unminimize code with chatGTP. It's fun and often fails :). From A to B here took me several attempts and breaking down the problem for chatGTP.

A: https://jsfiddle.net/3jvcx075/3/

B: https://jsfiddle.net/2083wfqg/ (still not 100% correct as the author notes: https://twitter.com/KilledByAPixel/status/162710257110918349... )

Re: CheatGPT

#524

Post by iameli »

dinkumthinkum wrote: post #461
iameli wrote: post #284

Earlier quoted context omitted.

People seem so convinced of this and I just don't get it. I'm seeing this comment through my eyeballs, generating some pertinent text in my brain, and outputting it back out. But so many people seem convinced convinced this process is something radically, fundamentally, irreducibly different than what ChatGPT is doing internally, and I don't get why. Is it because I have a consciousness with an internal narrative and…

You’re comparing a LLM to yourself, really? I wonder how many people talking about this know much about computers. Your cognitive capability is much more complex than ChatGPT. I’m not sure why people are convinced that a Turing Machine can simulate it, let alone do it efficiently. Do you believe that the way you think is at all like ChatGPT. That you are both processing text is not evidence. How many watts of power d…

Your argument is that my brain is more energy-efficient than ChatGPT, therefore... ChatGPT is incapable of "understanding"?

Re: CheatGPT

#525

Post by thro1 »

resource0x wrote: post #211
brycedriesenga wrote: post #190

Earlier quoted context omitted.

You can use this for that: https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain (GPT + WolframAlpha + Whisper)

I tested several AI chats, and none of them could correctly answer the question: "what is heavier, 1 kilogram of nails or 1 kilogram of feathers?". Does this one know? (I don't have openai key, can't test it myself). EDIT: turns out, the latest version of chatGPT knows the answer. They also fixed the answer to another famous trick question("The son of my father, but not my brother. Who is that?")

All wrong. Hot air is lighter than normal (make a google search). What weight of the baloon with 1kg hot and 1kg liquid air you will measure on Earth ? Does one fly or not ? What could you lift: 1 ton of air or 1 ton of iron ?

What are you trying to do - to brainwash your own, poor language model ?

Re: CheatGPT

#526

Post by BoorishBears »

hgsgm wrote: post #290
BoorishBears wrote: post #278

Earlier quoted context omitted.

> Will this filter cut many of the best engineers? It won't cut out a single good engineer, let alone the best. > I'd assert that the engineer who doesn't assume an unspoken implication, but instead qualifies their answer, or tells you when they cannot answer, or asks for clarification... is more likely to be the one who can make a system that works, and tell you when a system will not work. You grouped the one optio…

My organization values technical correctness.

If you need to settle for technical correctness that's fine.

Fortunately we have the resources to hire for technical correctness and a bit more than the minimum when it comes to being well rounded with your ability to understand problems, communicate, etc.

We don't want people who jump to conclusions like "the interviewer is asking me to recall things I don't remember" under the guise of "precision" instead of just asking

It takes commensurate pay/interesting work/an attractive workplace/etc. which are out of a single interviewer's control, so I never hold it against those who don't filter to any of that.

Re: CheatGPT

#527

Post by tacocataco »

sanderjd wrote: post #289
josh2600 wrote: post #123

So most interview questions like "make a binary tree" are dead. The best interview question that will never die: "What's the weirdest bug you debugged? What made it weird?" For posterity: https://www.gamedeveloper.com/programming/my-hardest-bug-eve...

In my last round of interviews, by far my favorite session was "here is a real project with a real bug, debug it, then if you have time, describe how to fix it, then if you have time, write the fix". (At Stripe FWIW.) It was super representative of what my work is actually like, and what I'm good at, and ChatGPT would not have figured it out. yet

Did they pay you for doing the interview?

Re: CheatGPT

#528

Post by oehpr »

QuadrupleA wrote: post #405

With all these ChatGPT academic apocalypse stories, I keep thinking - what the hell is wrong with students, that they don't want to actually learn the subjects they've enrolled in? If your goal is to fake-learn and have ChatGPT do your homework, just drop out already. You're paying big tuition for no educational benefit. Maybe your degree gets your foot in the door at some company, but it won't be too long before the…

I would agree with your position on the assumption that the skills being taught by universities are truly valuable.

My computer science and engineering course didn't teach git. I got a test on CSS and I wasn't allowed to use references, I assume the presumption was that I might need to write CSS without the internet I suppose? It introduced a proprietary UML code generator meant for working with oracle. There was 0 percent chance that company wasn't giving my university kickbacks. Speaking of kickbacks, have you looked at the insanity university textbooks are engaging in now?

If I had a choice of hiring someone who had field experience over someone with a degree, it wouldn't even be a choice for me, field experience. But you can't quantify that. you can't CYA with that. So this farce must go on.

Now, obviously, we should improve these issues. Obviously, that piece of paper should mean something. And hey I'm not saying I learned nothing. Despite these failings I managed to learn some valuable skills while I was there. I did take it seriously. But that made these issues all the worse. I would not operate on the assumption that if someone cheated their way through university that they have no skills.

Re: CheatGPT

#529

Post by sanderjd »

tacocataco wrote: post #527
sanderjd wrote: post #289

Earlier quoted context omitted.

In my last round of interviews, by far my favorite session was "here is a real project with a real bug, debug it, then if you have time, describe how to fix it, then if you have time, write the fix". (At Stripe FWIW.) It was super representative of what my work is actually like, and what I'm good at, and ChatGPT would not have figured it out. yet

Did they pay you for doing the interview?

No of course not.

Do you mean this debugging interview in particular, because it could potentially be useful work fixing a real bug for them? To be clear, it isn't an extant bug. I think the way they do it is they take an interesting (but fairly straightforward) real bug that they fixed at some point, and they back out the fix.

Re: CheatGPT

#530

Post by boroboro4 »

JohnFen wrote: post #511
boroboro4 wrote: post #377

Earlier quoted context omitted.

I’ve just asked gpt3 to sum two large random numbers and it gave me correct sum of them. Then I’ve defined fibanachi like sequence (f1=1, f2=1, fn=fn_1 + fn_2 + 7) and it correctly gave me the value of 10th element. It’s not just statistical model to generate something resembling training set, it does understand training set, to similar extents as we understand world around us…

I don't see how your example demonstrates your hypothesis, though. Summing two numbers and telling the next number in the Fibonacci sequence would be expected from a deep and complex statistical modelling of the existing internet data.

Both of these examples show GPT not barely approximating outputs (which doesn’t exist in real worlds for these inputs) based on training set but understands algortihms and able to apply them. I don’t believe our brains are doing anything different from that.
Post reply on HN