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

71–80 of 752 posts

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

#71

Post by di456 »

DoingIsLearning wrote: post #66
jmann99999 wrote: post #15

Generally rewriting emails for clarity... but I found another neat use of GPT-4. For public APIs, I ask to make sure its aware of the api. Then I ask for endpoints. I find the endpoint I want. Then I ask it to code a request to the endpoint in language X (Ruby, Python, Elixir). It then gives me a starting point to jump off from. Thirty seconds of prompt writing saves me about 20 minutes of getting setup. Yes, I have…

> Generally rewriting emails for clarity... This is the sort of thing that will force a lot of legal teams to shutdown access to GPT-4 api/gui from internal networks. Ppl never think of unintended consequences. Ask it a prompt fine but don't provide internal information as an input.

A couple more years of chip improvements and it may run self contained within a device.

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

#72

Post by jmann99999 »

DoingIsLearning wrote: post #66
jmann99999 wrote: post #15

Generally rewriting emails for clarity... but I found another neat use of GPT-4. For public APIs, I ask to make sure its aware of the api. Then I ask for endpoints. I find the endpoint I want. Then I ask it to code a request to the endpoint in language X (Ruby, Python, Elixir). It then gives me a starting point to jump off from. Thirty seconds of prompt writing saves me about 20 minutes of getting setup. Yes, I have…

> Generally rewriting emails for clarity... This is the sort of thing that will force a lot of legal teams to shutdown access to GPT-4 api/gui from internal networks. Ppl never think of unintended consequences. Ask it a prompt fine but don't provide internal information as an input.

Yeah, I have found I need to be careful. When I have used it, there is no confidential information in the email. I do pay attention to that.

That said,I think it will be interesting as Microsoft introduces this into Office 365. You bring up a great point. Most people will not realize they are sending potentially confidential information to Microsoft.

Perhaps it's no different than Grammarly... But I think you are right that legal departments are going to be all over this.

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

#73

Post by teaearlgraycold »

* Give me a bash one-liner to generate a secure random string

* I'm using a NextJS middleware function by exporting it from my page component like this ... Here is the middleware source ... But I get this error ...

* How can I tell if my site is running in production in NextJS?

* NextJS says localStorage is not defined. What should I do?

* Please adjust this Prisma schema so that there is an index on github_id

* How do I configure eslint to accept switch style that looks like ...

* Write hex bytes that represent a 16x16 bmp image favicon (didn't work lol)

* Please write me a React reducer and React context that holds state for a users's auth token and also synchronized that token into `localStorage` with the key `__auth_token`.

* How do I disable the rule "@next/next/no-img-element" on the next line?

* Here's my current page ... What changes should I made so that the footer is at the bottom of the screen when there isn't enough content to push it down to the bottom of the page. But if there is a lot of content it will sit right below the end of the content and not on the bottom of the screen.

Generally it works really well!

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

#74

Post by sgillen »

arwhatever wrote: post #5

I’ve been using it to generate bash scripts because I don’t know bash scripting, and also have it generate regexes for me to search for code references in a programming language where the “find all references” functionality don’ doesn’t work quite well.

I’m the same way, I “know” bash but I’m not fluent in it, always have to look up how to do very basic things like looping. But for the simple things I need bash for ChatGPT does great as a time saver.

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

#76

Post by pncnmnp »

oidar wrote: post #64
pncnmnp wrote: post #48

Earlier quoted context omitted.

That is an excellent idea! Perhaps someone should consider developing a smart diff tool for this purpose. To be honest, my work style can be a bit lazy at times, and this may reflect in my approach. My tool simply copies any changes directly to the clipboard. I then replace them with the original text and make adjustments on the same page. However, for more complex workflows, your approach is awesome. It could potent…

Oh yes, GPT-4 is much more compliant when asked to revise. GPT-3 sticks to it's guns when it thinks it is correct.

Ah, that's interesting! It could be related to the improvements they seem to have made in the area of "overreliance". According to OpenAI's paper (https://arxiv.org/pdf/2303.08774.pdf):

> Overreliance occurs when users excessively trust and depend on the model, potentially leading to unnoticed mistakes and inadequate oversight.

> At the model-level we’ve also made changes to address the risks of both overreliance and underreliance. Weve found that GPT-4 exhibits enhanced steerability which allows it to better infer users intentions without extensive prompt tuning.

> To tackle overreliance, we’ve refined the model’s refusal behavior, making it more stringent in rejecting requests that go against our content policy, while being more open to requests it can safely fulfill. One objective here is to discourage users from disregarding the model’s refusals.

> However, it’s worth noting that GPT-4 still displays a tendency to hedge in its responses.

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

#77

Post by unixhero »

jmann99999 wrote: post #72
DoingIsLearning wrote: post #66

Earlier quoted context omitted.

> Generally rewriting emails for clarity... This is the sort of thing that will force a lot of legal teams to shutdown access to GPT-4 api/gui from internal networks. Ppl never think of unintended consequences. Ask it a prompt fine but don't provide internal information as an input.

Yeah, I have found I need to be careful. When I have used it, there is no confidential information in the email. I do pay attention to that. That said,I think it will be interesting as Microsoft introduces this into Office 365. You bring up a great point. Most people will not realize they are sending potentially confidential information to Microsoft. Perhaps it's no different than Grammarly... But I think you are rig…

They already are. It is 99% stored on a Sharepoint on a Teams site anyways

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

#78

Post by endorphine »

whateveracct wrote: post #38
arwhatever wrote: post #5

I’ve been using it to generate bash scripts because I don’t know bash scripting, and also have it generate regexes for me to search for code references in a programming language where the “find all references” functionality don’ doesn’t work quite well.

I didn't know bash scripting and then I wrote some scripts and then I knew bash scripting and use it for lots of stuff. Has ChatGPT resulted in learning by doing for you?

Off topic: the similarity of yours and the parent's usernames was a funny little coincidence.

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

#79

Post by DotaFan »

I think all of our stories will look the same, we all ask about small problems, to get an answer as accurate as possible. It did help me in something else. If someone has a weight problem, you can ask ChatGTP to plan you an eating schedule. I've lost 6kg in 2 months now by eating healthy food. If someone is interested what questions I've asked, I've asked ChatGTP to create me a weekly meal schedule, where for my current weight, activity, height, I will be able to lose 0.5kg per week.

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

#80

Post by jinay »

I noticed my productivity with GPT was closely tied to how quickly I could access it. For example, Copilot is so useful to me because it's directly integrated into the browser. So I decided to build a Spotlight Search-esque interface to GPT that I could access anywhere [1]. It's been useful in answering quick questions or drafting documents.

[1] https://github.com/JinayJain/gpt-anywhere

Post reply on HN