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

Ask HN: How are you using GPT to be productive?

news.ycombinator.com

Post reply on HN
Print view View original

671–680 of 752 posts

Re: Ask HN: How are you using GPT to be productive?

#671

Post by throwaway4aday »

roflyear wrote: post #591
throwaway4aday wrote: post #364

Earlier quoted context omitted.

If you share your prompts then we could help. The most generally applicable thing I can think of is that you have to drop your old habits from using search engines, those types of queries will not get you very far. You have to talk to it like you would talk to someone in your company Slack/Teams/whatever chat and explain what it is you're trying to do and what tools you want to use to do it. Then ask it to refine its…

I'm not talking about informational stuff.

Cool, if you don't want to talk about it that's ok. In that case I'd suggest looking up one of the various prompt libraries and learning from there.

Re: Ask HN: How are you using GPT to be productive?

#672

Post by cutemonster »

andsoitis wrote: post #184
yosito wrote: post #177

Earlier quoted context omitted.

Yeah, I gave it a simple task of encoding a secret message in a sentence by using the first letter of every word. Hello = "Hey everyone, lick less onions". I worked with the prompts for over an hour to try to get it to complete the task, and while I did have some success, it really struggled to reason about the task or provide a valid response. If it can't even reason about a child's game, I can imagine it struggles…

> I don't think it's actually reasoning about things at all, just providing a statistically plausible response to prompts. It turns out that humanity’s problem might not be that AIs can think but rather that humans believe that AIs can think. One might even go so far as to say there’s a real danger that we hallucinate that AIs can think, to our detriment.

> problem [...] that humans believe that AIs can think

Definitely some people are going to believe this, eventually?

People already bow to statues and worship various invisible gods -- the AI programs would be so much simpler to start worshiping? When they can speak (if there's a loudspeaker) and generate text about them being alive and don't want to be switched of. And that everyone should obey their command. -- Wait 15 years and we'll see what new sects have appeared?

Re: Ask HN: How are you using GPT to be productive?

#673

Post by flipper88 »

yosito wrote: post #177
carlmr wrote: post #137

Earlier quoted context omitted.

So on my coding problems I haven't had much luck. It doesn't seem to know Bazel, the Rust code I asked about was completely hallucinated, but it did solve a problem with Azure DevOps I had. I think if the training set did not contain enough of something it can't really think of a solution. What is really nice though it's as you say the refinement of questions. Sometimes it's hard to think of the right query, maybe yo…

Yeah, I gave it a simple task of encoding a secret message in a sentence by using the first letter of every word. Hello = "Hey everyone, lick less onions". I worked with the prompts for over an hour to try to get it to complete the task, and while I did have some success, it really struggled to reason about the task or provide a valid response. If it can't even reason about a child's game, I can imagine it struggles…

[dead]

Re: Ask HN: How are you using GPT to be productive?

#674

Post by cmrdporcupine »

fhd2 wrote: post #268
fisf wrote: post #239

Earlier quoted context omitted.

Understanding a topic and letting chatgpt do repetitive and simple boilerplate stuff are not exclusive.

I'm fascinated by people saying they use GPT for boilerplate. Whenever I find myself doing simple/repetitive stuff, I tend to stop in my tracks and make that go away. Usually following the rule of three: If I do something for a second time, I don't generalise/generate just yet. If I need it a third time, I sit down and do it. Is that unusual? That said, I am mostly working with high level languages that make this gen…

Where I have found GPT and/or tools like that somewhat useful when playing with them is in writing tests.

Boilerplate code is usually refactor-able away, yes.

But tests are kind of intrinsically boilerplate by definition. There are test and fuzzing and provability systems that definitely help automate. But on the whole, writing a test harness + unit tests is often like writing the whole system over again.

I feel like this might be the one long term useful thing I get out of these coding assistants for my own work: read this interface and implementation I've written. Now write a boatload of negative test cases to verify correctness.

Re: Ask HN: How are you using GPT to be productive?

#675

Post by d1sxeyes »

andsoitis wrote: post #184
yosito wrote: post #177

Earlier quoted context omitted.

Yeah, I gave it a simple task of encoding a secret message in a sentence by using the first letter of every word. Hello = "Hey everyone, lick less onions". I worked with the prompts for over an hour to try to get it to complete the task, and while I did have some success, it really struggled to reason about the task or provide a valid response. If it can't even reason about a child's game, I can imagine it struggles…

> I don't think it's actually reasoning about things at all, just providing a statistically plausible response to prompts. It turns out that humanity’s problem might not be that AIs can think but rather that humans believe that AIs can think. One might even go so far as to say there’s a real danger that we hallucinate that AIs can think, to our detriment.

I am personally more worried by the concept that potentially humans believe that humans can think, and in reality, what we consider to be intelligence is not much more than a flesh-and-bones LLM.

Re: Ask HN: How are you using GPT to be productive?

#676

Post by spaceman_2020 »

roflyear wrote: post #592
spaceman_2020 wrote: post #374

Earlier quoted context omitted.

I’ve found that whenever it gets something really wrong, it’s either corrected by a follow up prompt (telling it that its wrong helps), or rephrasing the question.

Nope, not my experience - unless it's a trivial problem. In my experience it almost always gets stuck in a loop where it's rotating between two or more incorrect implementations. It isn't doing iteration - it's just looping. Even if I point out the problem directly, it will just say "sorry, you're right - here's the correction!" and the correction has the same response from an earlier item that I pointed out had a pr…

Used to get that a lot with GPT-3.5. But GPT-4 has been more reliable if you rephrase your prompt.

Re: Ask HN: How are you using GPT to be productive?

#677

Post by roflyear »

imiric wrote: post #660
roflyear wrote: post #356

Earlier quoted context omitted.

Don't make stuff up. There is no indication that will happen.

It has already happened: - https://news.ycombinator.com/item?id=35236275 - https://news.ycombinator.com/item?id=35248704 - https://news.ycombinator.com/item?id=35228808

Absolutely not what was suggested, but ok.

Re: Ask HN: How are you using GPT to be productive?

#678

Post by roflyear »

sd9 wrote: post #664
roflyear wrote: post #588

Earlier quoted context omitted.

Explain how it improved. Yes, it has improved accuracy (test taking) but it still gets stuck in the same loops over and over: "response has issue A" -> point out issue A to GPT "response has issue B" -> point out issue B to GPT GPT replies with the response that had issue A ... This is not a tool that is going to be good at performing generic tasks. It just isn't.

I said that the context window improved. I mean that it is larger. GPT-3.5 is 4k tokens, GPT-4 is 8k tokens (standard) or 32k tokens (only API access atm). This is the number of tokens that GPT-X can take into account when producing a response. Specifically, I was using this to support the statement "In very near future your IDE will send the whole codebase as context to LLMs." I'm not talking about loops or accuracy…

It's true, but there is no indication that GPT can explain larger concepts for you, and negative indication it will be able to do it accurately.

It can't even explain small code to me unless it is something that it has been trained on. Often it gets even simple things wrong, either obviously, or worse, subtly wrong.

Re: Ask HN: How are you using GPT to be productive?

#679

Post by roflyear »

throwaway4aday wrote: post #671
roflyear wrote: post #591

Earlier quoted context omitted.

I'm not talking about informational stuff.

Cool, if you don't want to talk about it that's ok. In that case I'd suggest looking up one of the various prompt libraries and learning from there.

I'm just not talking about trying to fish an accurate answer. I think you can do that. I'm talking about getting an answer about something that requires an interaction that gets the model to "understand" the problem (like you would a person) - which GPT can't do.

Re: Ask HN: How are you using GPT to be productive?

#680

Post by roflyear »

spaceman_2020 wrote: post #676
roflyear wrote: post #592

Earlier quoted context omitted.

Nope, not my experience - unless it's a trivial problem. In my experience it almost always gets stuck in a loop where it's rotating between two or more incorrect implementations. It isn't doing iteration - it's just looping. Even if I point out the problem directly, it will just say "sorry, you're right - here's the correction!" and the correction has the same response from an earlier item that I pointed out had a pr…

Used to get that a lot with GPT-3.5. But GPT-4 has been more reliable if you rephrase your prompt.

Have not had that experience with GPT-4. But that is almost unusable for me anyway because it's crazy slow (during US working hours anyway, it's faster at night) and the rate caps get hit before we get anywhere.
Post reply on HN