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

481–490 of 752 posts

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

#481

Post by HervalFreire »

ornornor wrote: post #460
tux3 wrote: post #456

Earlier quoted context omitted.

>What if it’s advice is wrong or makes you worse in the long term because it’s just regurgitating whatever at you? What if you talk to a human, and their advice is wrong or makes you worse off in the long term, because they're just repeating something they heard somewhere? Here's my advice: Don't accept my advice blindly, humans make mistakes too.

Of course, but an AI can't explain how it got to what it's telling you. A human can, and you don't have to accept it wholesale; it's possible to judge it on its merits and argument. But no-one really understand how and why ChatGPT says what it does, so you can't trust anything it says unless you already know the answer. In this discussion, a human has studied psychology and has diplomas or certifications to prove it,…

Most science in the social science is essentially black box studies. We see what goes.in and observe what comes out without any formal understanding of what goes on in the box itself.

Additionally there's something called the replication crisis in the social sciences (psychology included) which is basically to the effect of a major discovery that most of these "black box" studies can not be reproduced. When someone runs the same experiment the results are all different.

It goes to show that either many of the studies were fraudulent or statistical methodologies are flawed or both.

Given that chatGPT therapeutic data is ALSO derived from the same training data I would say it's ok to trust chatGPT as much as you would trust psychologists. Both have a lot of bullshit with nuggets of truth.

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

#482

Post by swader999 »

Volrath89 wrote: post #244
Marcan wrote: post #203

Earlier quoted context omitted.

Thank you for your well written response. I found it informative as I'm also currently exploring ways to leverage ChatGPT in my daily workflow. I also found it interesting that your answer kind of mirrors the writing style of ChatGPT, especially at the end there. I'm not saying you used it to write that response by the way, just that it may become more and more common for people to adopt this style the more ChatGPT's…

I suppose it was part of the "joke", but YOUR answer is the one written in ChatGPT style, not OP. I was thinking that maybe in the near future it will be "better" to write with a couple of mistakes here and there just to prove your humanity. Like the common "loose" instead of "lose" mistake, it will be like a stamp proving that you are a human writing.

I do that when I write grants for my sports club and it seems to get better results than peers that hire pros to apply for them.

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

#483

Post by toastar »

I’m new to writing contracts and agreements, and ChatGPT has replaced Google as a point to jump in and start building these documents without having to wade through pages of unhelpful SEO tuned search results and then pick and choose clauses from sets of often irrelevant samples.

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

#484

Post by unboxingelf »

Mind blown example from last week:

  Implement the following repository interface against sqlite in Golang. The method receivers should be defined on a struct called “repo”.
The code used prepared statements and worked out of the box. I wrote unit tests to verify.

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

#485

Post by HWR_14 »

anoy8888 wrote: post #207
lionkor wrote: post #196

Earlier quoted context omitted.

i think most people will just keep programming the way they do, and the AI hype will mostly die down. People have been saying that C++ is dead for decades, yet here I am writing code in it with a big community of others who do, too.

I think this is the problem. When people talking about c++ is “dead” ,at that time they meant 70% people using to perhaps 5% . Just like we says after industrialization,making clothes by hand is dead . It is irrelevant that there are still some people making clothes by hand . When AI the main way to code and remove 90% of coding jobs. It is also irrelevant to state that there are still 10% people still coding

When people say C++ is dead, they normally are looking at public repos and stack overflow questions. Fairly biased towards newer languages

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

#486

Post by HervalFreire »

utopcell wrote: post #470
hermannj314 wrote: post #349

I have a few conversations going. My most productive is a therapy session with ChatGPT as therapist. I told it my values, my short term goals, and some areas in my life where I'd like to have more focus and areas where I would like to spend less time. Some days we are retrospective and some days we are planning. My therapist gets me back on track, never judges, and has lots of motivational ideas for me. All aligned w…

I wonder if the three laws of robotics are already weaved into the LLM. Seems like a necessary step for this kind of usage.

Those rules weren't meant to generate societal harmony. They were made to have a contradiction which in turn could generate a good plot.

Remember what happened in Isaac Asimov's iRobot?

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

#487

Post by HWR_14 »

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…

ChatGPT doesn't understand the components of words (letters, syllables) very well.

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

#489

Post by devinprater »

So, I'm a part of a small team, each member doing something different. I handle a Moodle curriculum, I hate Moodle BTW, and teach students. And do monthly reports for the students I teach. They're adults, so it's not too hard. Usually.

Anyway, GPT3.5 couldn't always get lessons right. It'd say to scroll with VoiceOver on, on the iPhone, that you'd swipe up with two fingers. Nope, that's three fingers. I can simply ask the bot to correct it, and it'd do so. That, I think, is one of the cool things about it. I had it build a Python script that can take a TSV file exported from Excel cause the cafeteria staff that give students food just can't possibly just write out the menu in a list, oh no that's just too hard, it's gotta be all fansy in Excel with hard to parse columns of letters of days with the menu beside it /s. Anyway I had it create a Python script to just turn that into HTML. It's still awful, just on a web page and the lunch CLI app I wrote a year ago can't parse this new format.

Another thing I just thought of is making ringtones. I can start playing a song, stop at the start of it, write that time down, play till the end of the ringtone, write that time down, and get GPT to give me an FFMPEG command to make a ringtone, with that filename included in the command so I can't even have to copy and paste into the terminal window. That'll be pretty cool.

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

#490

Post by jjeaff »

sharperguy wrote: post #249
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…

I've found that it's much worse for languages like rust than it is for things like typescript and python. The thing AI seems to be really great at is writing boilerplate code like argument parsing for CLI tools.

I wonder if that is simply due to orders of magnitude less training data for rust code. Python and JavaScript are ubiquitous. While rust is 7 years old and makes up less than 2% of the code on GitHub.
Post reply on HN