Live data from Hacker News

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

news.ycombinator.com

621–630 of 752 posts

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

#621

Earlier quoted context omitted.

Why exactly? Privacy? OpenAPI is currently experiencing the fastest- and by choice- absorption of personal and corporate data of any major tech company and so is rapidly growing materially useful and unique personal datasets of large swaths of the digital population. Sure it isn't emails or website visits...yet. Different from Google? Not really.

As you said it: Google already does this too, so why not use something that, currently, has less SEO blogspam or ads?

Plus, even if it is just regurgitating top links, if is something you can ask a question and then go to another tab to do something for a minute and then come back and there is exactly what you asked. Ignoring ads, you still have to comb through so much text of information that is, at that time, uesless to your needs when you go to any of those top links.

Plus, GPT is likely pulling from multiple sources at once and VERY quickly.

I'm so confused by the people that keep arguing this about just using Google. It's clear why it is easier to use GPT. Is it always correct? No. But, are you certain the info on the site you just navigated to through Google search results is any more correct? If it is a topic you know nothing about them how would you be any wiser either way?

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

#622

Earlier quoted context omitted.

Can you explain how ChatGPT's soccer itinerary is any different from the top google search [1] for the subject? Is ChatGPT's response any more useful or meaningfully different from the practice routines at the link? [1] https://www.soccerhelp.com/soccer-practice-plans.shtml

What makes you think the top google result wasn’t written by chatgpt? I came across an article on volleyball the other day that was the top hit for what I was searching for - halfway through the article there was a paragraph about a famous setter from Nekoma’s volleyball team and how they were going to play in the upcoming spring nationals. The “author” seemed completely unaware that Nekoma is a fictional team from t…

No real knowledge of volleyball or Manga but either way that is pretty hilarious. Also how lazy? Lol Even if you have AI do your work, at least proofread it.... And fact check.

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

#623
post #288

I just asked it to make an itinerary for a 45 minute long 6 year old boy's soccer practice. It was almost perfect. It needs to be tweaked (3 minutes for cool down?) but it did 95% of the heavy lifting. I also asked it for vacation ideas with nice cabins and trailer hookups with outdoor activities for kids and nice cabins within 200 miles of where I live - it was almost perfect in its response. I have trouble starting…

> I have trouble starting things from scratch, but once a framework exists I'm usually solid and can refine it to where I want it. This is so true for GPT’s benefit. As an anecdote here: We wrote some C++ code involving multiple HTTP servers, where while we ultimately wrote the exact code we wanted ourselves, but the starting code provided to us by ChatGPT really helped speed up the process to having finished off the…

That's starting point really is very draining for some of us. Sounds like you too. The dead-eyed, blink-once-every-two-minutes stare while moving through documentation, stack override, Google, etc.

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

#624
post #593

Earlier quoted context omitted.

If you eliminated 100% of my code typing time with perfect effectiveness I think that'd make me maybe 10% or 20% more productive? Turning ideas of what the code should be doing into code just isn't a bottleneck for me in the first place. Are there people who just add net 1000 lines of code to whatever they're working on every single day or something?

I keep seeing this point made, but AI tools don't save you just typing time. They save you time you would previously use to lookup documentation, search the web and Stack Overflow answers. They save you time it takes to navigate and understand a codebase, write boilerplate code and tests, propose implementation suggestions, etc. Dismissing them on the basis that they just save you typing time is not seeing their full…

Navigating and understanding a codebase is the only one of those which would excite me, but it's also something I've never even someone propose using ChatGPT for. Do you have an example of what that would look like?

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

#625
I just used this to create and integrate a new component(layout) in one of Hugo's theme. I wanted to view lists as cards and using GPT saved me a lot of time. Im not a frontend developer and i dont know how to start writing some code, but i am able to verify and modify when i have it. Its also a lot faster to get proper responses or directions through chatGPT than from google.

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

#626
post #123

Since I use ChatGPT regularly, I decided to create my own client. I prefer to avoid third-party services that require privilege escalation like Grammarly and Copilot. I have developed distinct profiles for different tasks, each with its own system prompt and input method. After getting the hang of it, I plan to tweak the parameters as well. Here are some of the profiles: Explainer: a default, general purpose Q&A. The…

Yeah, I built myself something similar for 1-shot tasks[1], examples[2]. [1] https://files.littlebird.com.au/Screen-Recording-2023-03-26-... [2] https://files.littlebird.com.au/Shared-Image-2023-03-26-10-3...

Nice! I would like to see more examples out there that do not limit the experience to only a text/chat interface. It is becoming tiring to repeatedly add extra prompts and format the input/output manually.

I found that some workflows can be executed more efficiently by using GUI/form controls (like the "simplify" button for proofreader). Node-based UIs would also be ideal for some design-related tasks. Builders have already started experimenting with these, I guess, and I'm excited to see what they come up with.

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

#627
- Asking coding questions is the most common use I have seen. But it doesn't always give the correct answer. That's fine. At least it points to the right direction. Since it has the context it's easier to ask follow up questions.

- Finding new tools. Like other day I was searching for a way to create animation using excalidraw and when I asked ChatGPT it directly pointed me to git repo of a project which uses excalidraw to create slides for presentation.

- ELI5: It does do decent job for this. But not always.

- Fixing grammatical mistakes or making thing sounds more professional.

- Finding alternative for some solution.

- Generating digram for some flow via mermaid code or digram for code.

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

#628
Summarized all the comments in this page using chatGPT and grouped them.

# Programming and coding assistance

-To improve code by making it simpler or reducing duplication.

-To generate code for straightforward tasks with clear-cut objectives.

-Writing code in a language that one is not familiar with.

-To get help with design patterns in software development.

-Spotting libraries, methods, or alternative ways of doing work that people usually do but in a different fashion.

-Writing code or fixing bugs in a specific algorithm, method, or SQL query.

-Automating email to draft responses and summarize important received emails

-To generate test cases, identify performance issues or bugs in code, and convert layouts from Android XML to Compose.

-Help with writing unit tests by providing basic boilerplate templates and speeding up the work by 25%.

-Building bindings for a library, creating simple schemas for a microservice, and solving a one-to-many relationship problem.

-Using OpenAI as a virtual assistant to set reminders or access calendars.

-Writing code: OpenAI's GPT can provide suggestions on APIs or variables to use, saving users time researching and helping them write more efficiently.

-Writing commit messages: Some users use GPT to generate commit messages for their Git repositories, saving time and mental energy.

-Learning programming languages or technologies, such as PowerShell, by using OpenAI to create initial solutions that users can refine and iterate upon.

-Generate complex queries or configuration files

# Automation and efficiency in day-to-day tasks:

-Summarizing and finding answers to specific questions on various topics, including tax questions, recipes, and movie suggestions.

-Transforming data, such as changing raw citations into bibtex entries, fixing spelling mistakes, or converting CSV files into JSON.

-Outsourcing corporate emails to ChatGPT to convert them quickly and easily.

-Document search and learning new systems.

-Converting code: using OpenAI to convert code from one language to another, like from bash to Golang.

-Model classes and JSON: using OpenAI to create a Java class using Lombok from JSON and create JSON from a Java model class.

-Writing specifications: using OpenAI to write the rest of a specification after writing some part of it, saving time.

-Generating boilerplate ADS docs for detection content, converting rules between various query formats, identifying and normalizing security data, and brainstorming how to approach novel detection use cases in the cybersecurity field.

# Language learning and translation:

-To learn a foreign language by getting errors corrected and grammar concepts explained.

-Asking questions to improve writing, better understand concepts.

-Language learning: using OpenAI to learn conventions in a programming language one is not familiar with.

# Creative writing and brainstorming:

-Generating plausible scenarios for various training programs or creating standard terms of service for an app.

-Generating ideas for creative tasks, such as brainstorming, writing, and lesson planning.

-To lower the emotional-resistance barrier to doing creative tasks and improve the quality of the output.

-Creating crossword puzzles and word-finding puzzles.

-Creating lesson plans for various topics.

-To workshop different ML ideas by combining different ideas from the literature.

-To do bizarre linguistic experiments with writing prompts.

-Creative naming: using OpenAI as a creative partner to help with naming things like a data warehouse.

-Generating names for projects or classes and debugging help.

-Write SOPs, write emails, and analyze tone.

-Aid in the writing process, including transforming thoughts into presentable versions.

-Writing contracts and agreements.

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

#629
post #218

Follow up question, how come discussions like this rarely mention virtual assistants like Siri/Alexa/etc? So many use cases overlap, there’s potential for improvements but Siri still struggles to understand context and gpt has no way to access my calendar (at least in a way that I’d like). I guess this will change fast?

There's no UI, I think humans need a bit of affordance and are bad at keeping things in memory. So while it may be good in answers/understanding, the applications where it can be leveraged are more limited

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

#630
I haven't been using it for much besides simple problems that I don't feel like trawling through SO or banging my head against for 30 minutes. Things like shell one liners for text processing/searching files/etc.

On larger tasks, I've not found it particularly useful, although I haven't had a chance to try it out with GPT-4. Previously, when I would ask ChatGPT about solving a particular problem, it would be terribly broken. Maybe GPT-4 is better.

That said... even though the code was broken, it was helpful in that it gave me a skeleton of what a solution would look like, especially if it was a problem domain I had no experience in.

For example, I wanted to do a little project to extract text from PDFs, including PDFs that were basically image scans, so I would have to do some kind of OCR. I'd never done anything like this before. I'm sure I could spend time Googling and figuring out which libraries to use. But instead I asked ChatGPT.

The solution it gave wasn't great, but more importantly it pointed me in the right direction with the libraries it used and some examples on how to use it.

Aside from programming, I've also used it as a "study buddy" since I'm going back to school and working on my masters in Computer Science. That's been much more successful. For example, I will give it questions from study materials handed out by the instructor (like previous exams or quizzes) and say "We are reviewing paper X in this class. Here's questions from a previous exam. Please generate questions like this to help me prepare for my upcoming exam."

or "Here are questions from a previous exam and my answers. Please evaluate my answers and provide feedback."

or "Here are questions from a previous exam, please quiz me in a similar format"

Also working on projects for class, while I won't ask it to solve the problem for me, sometimes I'll bounce ideas off of it. Like... "I know there's an algorithm to do X, but I don't know the name of it. I don't want you to write the algorithm for me, because that's cheating, but please tell me what the algorithm is called and if possible point me to a good paper describing it."

Lastly, I recently used it while helping someone update their resume (with permission). I removed all personal information and asked ChatGPT-4 to help me make it pop. We had a little back and forth conversation on ways we could improve the resume, and when we were done it was pretty damn amazing. I'm pretty good at doing resumes, but me + ChatGPT was better than me alone.

Apparently it did a bangup job, because every interviewer went on and on about how good the resume was and how impressed they were.

Post reply on HN