Live data from Hacker News

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

news.ycombinator.com

701–710 of 752 posts

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

#701
Not part of any workflow per se, but I’m planning a trip to NYC this month and asked it to generate an itinerary that includes certain sights along with suggested places for lunch/dinner and subway directions. What it produced blew my mind! I simply couldn’t have done what it did on my own.

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

#702

Earlier quoted context omitted.

> 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. -- Wai…

You will not need 15 years - I'd give it the next election. Someone just needs to turn Q into a chatbot and we're basically there.

It’s like Twitter, but with bots.

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

#703
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…

Is this with Chatgpt or GPT4? The latter is supposed to be way, way better, according to this paper[1] [1] - https://arxiv.org/pdf/2303.12712

ChatGPT has a GPT-4 mode if you're paying for it.

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

#704
post #8

I often use it as a thesaurus. "Words that mean X" or even "that situation X me and I was annoyed - give me options for X" For programming, all sorts of things. I use it all the time for programming languages that I'm not fluent in, like AppleScript or bash/zsh/jq. One recent example: https://til.simonwillison.net/gpt3/chatgpt-applescript I use it as a rapid prototyping tool. I got it to build me a textarea I could p…

How often do you find yourself decoding abstracts?

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

#705
GPT Development Services are hard to come by! We provide end-to-end solutions so you can transform your business with cutting-edge GPT technology!

We, at Rather Labs, provide GPT development service. If anyone is interested, you can contact us: https://www.ratherlabs.com/gpt-development

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

#706
I have a basic understanding of multiple coding languages, but I don't have the time to learn the exact syntax or commands for each one. ChatGPT has given me so many tips and scripts on coding in VBA, M query, DAX, JavaScript, and more. I'm currently using it to customize a Power Apps solution, which would take me 10 times longer without ChatGPT.

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

#707
I remember reading an article a while back written by some senior engineer. He was explaining how the new generation of programmers peak in productivity very rapidly in their career because they lack complex problem solving skills and deep programming knowledge. He argued that Google and StackOverflow made it easy to solve problems without thinking deeply about things so it impeded their ability to solve more complex tasks later in their career when Google couldn't do the thinking for them.

If this is true, those new AI tools will probably exacerbate this trend. Fewer and fewer programmers will be able to think deeply about things and the global code base will lose in diversity as people rely more and more on the same AI models to generate code.

As the code loses in diversity, it will also lose in robustness, which increases the risk that something will go wrong for a lot of people all at the same time.

I try to do the thinking myself. Then I'll use one of those tools when I know what I want to write but I'm too lazy to do it.

I don't know man, I was working in the financial industry when 2008 happened. I see a lot of the same patterns and heureustics today in the tech world that led to the 2008 financial crash. When people start using advanced statistics to do the thinking for them, they get real complacent real quick and it rarely ends well. AI has it's limitations and we probably won't find out until we fly too close to the sun and we burn ourselves.

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

#708

Earlier quoted context omitted.

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.

Consider how long our comment thread is and I still don't have a clear idea of what you're talking about or how to help you.

I'm not looking for help, so I don't think we're really trying to have the same conversation.

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

#709

Earlier quoted context omitted.

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.

Something akin to: Here is a niche mathematical problem that does not fit any existing solutions/publications, we need a working but not necessarily optimal solution to do this. ?

Sure, or even an existing algo or method that is applied to something very niche that hasn't been done much (at least in the data GPT is trained on, I guess).

In my experience these things need a little nuance communicated as a part of the problem, but GPT can't get there. It just starts looping over incorrect solutions (rather than modifying them slightly to get it right like a person would).

These aren't crazy advanced things, either. I'm not a genius. I solved the problems when GPT couldn't. I was just trying out GPT4.

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

#710
post #177
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…

> I don’t think it’s actually reasoning about things at all

This is a huge leap. There’s plenty of humans who couldn’t do that, especially historically.

Stop thinking about reasoning as a binary question and think of it as a spectrum. Actually, not even a spectrum, but a huge multi-dimensional problem. ChatGPT does better at some reasoning problems than most humans do, and worse at some others. You clearly found one that it’s particularly bad at.

Post reply on HN