HN Explorer

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

629 points by yosito ↗ HN
With GPT so hot in the news right now, and seeing lots of impressive demos, I'm curious to know, how are you actively using GPT to be productive in your daily workflow? And what tools are you using in tandem with GPT to make it more effective? Have you written your own tools, or do you use it in tandem with third party tools?

I'd be particularly interested to hear how you use GPT to write or correct code beyond Copilot or asking ChatGPT about code in chat format.

But I'm also interested in hearing about useful prompts that you use to increase your productivity.

751 comments

[ 2.9 ms ] story [ 466 ms ] thread
monero-xmr
I have asked ChatGPT tax questions, some of which I knew the answers to and others not. I think it’s a great summarizer if the spammy blogs out there.

It’s great for bash one-liners with flags and OS-specific nuances.

Haven’t really been able to use it for really advanced things. But maybe someday.

tyoma
Be careful with tax questions.

I asked some for a moderately complicated tax situation and ChatGPT very authoritatively imagined a deduction that didn’t exist by combining two different but related parts of the tax code.

Freedom2
With the understanding that it's only trained up to Sep 2021, I'm using it to spot check for any libraries that have flown under my radar, or any other methods of doing work that I usually do, but in a different fashion.

Do I always get stuff that I can apply? No, not really. But given that discoverability can be low for things like that, it's usually helpful at finding me things to, at the very least, look into.

ricochet11
as an fyi its hallucinated libraries for me when writing python code, importing things that dont exist.
kaetemi
On the other hand, it can write hypothetical example code for a Python binding or conversion of a library in another language.
olalonde
Mostly just asking stuff directly on https://chat.openai.com/chat. Last 8 requests were (all successful):

- Asked it to improve a HN comment I wrote.

- Asked about an idiom I couldn't remember, by saying it in other words.

- Asked it to dumb down some things about options (finance) I didn't understand.

- Asked it if I could use the eBay API to list my purchase history (you can, and it knew how).

- Asked it to generate pretty standard Terms of Service for an app I'm working on.

- Asked it to generate a moderately complex Prisma (ORM) query that I described in natural language.

- Described what I wanted Nginx to do in natural language (e.g. "the index file will be served whenever no file is found") and asked it to output a configuration file.

- Asked it what the "XDG" in "XDG_CONFIG_HOME" stood for.

Also, occasionally ask it to generate shell commands using a CLI I wrote[0].

[0] https://github.com/clevercli/clevercli

jmknoll
Completely off-topic, but do you like prisma, and how are you using it (scale, complexity, solo vs team, etc).

I toyed around with it a while back, and it looked potentially awesome, but different enough that I was worried about using it on a work project in case it failed in some use case.

Im so sick of the SQL ORM situation in Typescript, but Prisma might have an answer.

olalonde
It's a solo project, CRUD stuff, but having used pretty much all JavaScript/TypeScript ORMs in existence, I can say that Prisma is way ahead of the competition. I would personally recommend it. A traditionally cumbersome and annoying thing about trying a new ORM is that you basically have to re-learn a pseudolanguage for building SQL queries but that hasn't been an issue this time, thanks to ChatGPT. So overall, happy with Prisma and plan to keep using it.
panzi
Prisma has this one glaring issue: https://github.com/prisma/prisma/issues/10649

Segmentation fault with NodeJS 18. Its about prisma having linked a different version of OpenSSL than NodeJS. A workaround is to use the "binary" engine, meaning you run another process, talk via IPC to that, and that then talks to the DB, which is ridiculously roundabout.

But this issue is finally worked on, so once that is fixed its good.

bottlepalm
It's good, but verbose, you can't select nested objects by just doing lesson.mapped.sections.course .. etc.. you have have to do something like

    lesson: {
        select: {
            id: true,
            slug: true,
            title: true,
            mapped_sections: {
                select: {
                    id: true,
                    slug: true,
                    section: {
                        select: {
                            id: true,
                            title: true,
                            course: {
                                select: {
                                    id: true,
                                    slug: true,
                                    title: true
lisasays
Asked it to generate pretty standard Terms of Service for an app I'm working on.

So you're using it generate a legally actionable document. Is this a good idea?

olalonde
Yes. I got a cheap AI lawyer if someone sues me, all good. All jokes aside, the alternative was to not have a "Terms of Service", so fairly sure it's better than nothing.
lisasays
Fairly sure it's better than nothing.

Until it isn't. Live and learn, as they say.

olalonde
Has there ever been a case of a ToS so badly written that not having one would have been preferable? I'd be curious to hear about that story if it exists.
lisasays
At a certain point in my life, I came to the conclusion that if something is important enough, it generally pays to: (1) either research the matter myself until I was satisfied that I understood the cost/risk tradeoff sufficiently; or (2) if I don't have the time or skills to do that, have the matter reviewed professionally. Both of which are alternatives to "doing nothing".

Employment or other contracts, health decisions, taxes ... that's how I roll.

That's just me, and I'm not you. It may also just be a hobby project or otherwise of negligible consequence. In which case it would seem to fall under the rubric of what generative AI is arguably suitable ("better than nothing").

namaria
Hiring professionals is often about transferring liabilities to knowledgeable people. I wouldn't want to respond for something done by some automatic tool whose output I don't fully understand.
[deleted]
(comment deleted)
[deleted]
(comment deleted)
olalonde
"Ain't nobody got time for that"... that's how I roll.
kyleyeats
It's an arms race. First nobody was reading them, now nobody is writing them.
mindcrime
Asked about an idiom I couldn't remember, by saying it in other words.

You inspired me to try it for finding a book I can't quite remember the title of. Unfortunately no joy. Still, for the amusement of anyone who is interested, or anyone who might be able to help me with this book:

---

Mindcrime: What was that horror novel from way back when, about the time traveling demon hound?

ChatGPT: It's possible that you're thinking of the horror novel "The Hound" by H.P. Lovecraft, which was first published in 1924.

In the story, two grave robbers become obsessed with obtaining a certain artifact from a tomb in Holland. After obtaining the artifact, a small bronze statuette of a hound, they begin to experience strange and terrifying visions. The hound appears to come to life and stalks them through their nightmares.

Later, one of the grave robbers travels to Egypt and discovers that the artifact was made by a sinister and ancient cult, and that the hound is actually a demon summoned from another dimension. The hound then follows the man back to his home in England, where it continues to torment him until he meets a gruesome fate.

It's worth noting that there have been many horror novels and stories featuring time-traveling demon hounds over the years, so if "The Hound" isn't the specific book you're thinking of, there may be another that matches your description.

Mindcrime: No, it was more recent than that. I think from sometime between the late 1980's to mid 1990's. I think the word "hound" might have been in the title.

ChatGPT: Thank you for the additional information! The book you may be thinking of is "The Hound of the Baskervilles" by Arthur Conan Doyle. Although it's not a horror novel, it's a detective story featuring the famous detective Sherlock Holmes and his companion Dr. John Watson investigating a supernatural curse and a demonic hound that is terrorizing the Baskerville family on their estate in Dartmoor.

"The Hound of the Baskervilles" was first published in 1902, but it has been adapted and retold in various forms over the years. There may be a horror novel that is a retelling or adaptation of the original story that you're thinking of, but without more specific details, it's hard to say for sure.

Mindcrime: No, it's much more contemporary than that.

ChatGPT: I apologize for the confusion. Let me try to narrow it down further. Do you remember any other details about the book? For example, do you remember the author's name or any other specific plot points or characters?

Mindcrime: There was some stuff about an airport or airplane near the end.

ChatGPT: Thank you for the additional detail! The book you might be thinking of could be "Watchers" by Dean Koontz.

"Watchers" is a horror novel that was published in 1987. The story follows Travis Cornell, a man who is hiking in the mountains when he stumbles upon a genetically engineered creature known as "The Outsider." The Outsider is a highly intelligent dog with extraordinary abilities that has escaped from a government laboratory.

Cornell takes the dog under his wing, but soon discovers that a ruthless government agent is after the dog and will stop at nothing to retrieve it. The novel reaches its climax at a local airport, where a final showdown takes place between the agent and the dog.

While "Watchers" does not feature a time-traveling demon hound, it does involve a genetically engineered dog that could possibly fit your description.

Mindcrime: No, it wasn't by Dean Koontz. And time travel was definitely a plot element.

ChatGPT: Thank you for letting me know. I apologize for not being able to find the book you are thinking of. Without more specific details, it's difficult to narrow down the possibilities. If you remember any other details about the book, please don't hesitate to let me know and I'll do my best to help you identify it.

nneonneo
Have you tried asking a story-identification question on https://scifi.stackexchange.com/? I've seen quite a few questions on there get answered with even the most obscure books or movies, and your question should fit right in on that site.
mindcrime
I've posted to a couple of places, but I don't remember exactly where all now. I think there was one sub-reddit and maybe something on Twitter or Facebook. I don't think I've tried scifi.se. I guess that is worth a shot. Thanks for the suggestion!
arwhatever
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.
whateveracct
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?
endorphine
Off topic: the similarity of yours and the parent's usernames was a funny little coincidence.
arwhatever
I guess I use ChatGPT similarly for Ruby and for Rust, but with the only difference being that in my mind I intend to “learn” those two.
sgillen
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.
jrmann100
I find ChatGPT most helpful as a "what's that called" tool. A lot of my queries are finding/confirming the right idiom when writing something, or getting a specific name out of a vague description (JavaScript concepts, shell commands, CSS selectors).

Search engines with SEO are so reliant on keywords that it often feels like I'm suggesting answers rather than asking questions - it's so refreshing to be able to just ask again.

echelon
It's replaced Google for the "what's that called" tool.

Google used to be good at that task, but it's sucked for the last four years or so. Whenever they gave up on search and leaned into sludge content plus ads.

ChatGPT is better than Google ever was anyway.

jhanschoo
I hope it's going to remain that way, but the realistic cynic in me tells me that using ChatGPT to discover stuff is going to increasingly suck more now that people are going to try to target ChatGPT for SEO.
jimnotgym
GPT is better than Google for something like, 'how do I implement nested blog post comments in Flask'

And much worse than Google for, "site:miguelgrinberg.com nested comments"

Unfortunately I don't know the equivalent of Miguel for everything I need to know, so on average I suppose GPT is better. However it also means that you may never discover the Miguel of your domain!

tbran
Dude! I just did that search and now I'm reading Miguel's blog. Good stuff! Thank you!
jimnotgym
You are most welcome. Now how do we make a search engine that finds the Miguel for every domain?
duckmysick
It's also helpful with explaining acronyms. Something like `What does SEO mean in "Search engines with SEO are so reliant on keywords"`.
victorbjorklund
Yea, this is great. I used it alot for this. When you kind of know what you wanna do but you dont know the technical term.

Like if you dont know it is called sharding but you know you wanna store stuff on several databases.

Me: I have a postgresql database but it has too much data in it. I wanna split the data in several databases. What is that called?

GTP: Splitting a database into multiple smaller databases is known as database sharding. Sharding is a technique used to horizontally partition large databases across multiple servers or instances in order to distribute the workload and improve performance. Each shard is typically hosted on a separate physical or virtual machine and stores a subset of the total data, allowing for more efficient queries and faster data retrieval.

Then i know what to google for

pncnmnp
A while back, I mentioned in a thread that I have found ChatGPT to be quite useful for correcting grammar and spelling errors (https://news.ycombinator.com/item?id=34781888).

Later, when they released their API, I developed a CLI tool for this purpose (https://github.com/pncnmnp/grammatical). Note that it is not flawless, but it works well. It has improved my writing productivity, both for blogging and emails.

oidar
I like your prompts for your script, I may integrate it into my workflow too. I have found that when I am editing my work, it is helpful to have the original sentence and the suggested sentence one after another. While this takes away the paragraph form, it clearly helps you tease out the "improvements" to either accept or reject. I also have GPT number the sentences. And then when I am done, I say - something like - "please assemble back into paragraph form, all revised sentences are accepted except numbers 5, 12." And then it reassembles the paragraph(s) with the revised corrections. I use ChatGPT (4) for really long stuff though... might not work with Turbo3.5.
pncnmnp
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 potentially transform the process into something similar to Grammarly.

Edit: Have you noticed any differences in terms of quality between GPT-4 and Turbo3.5 for this particular task?

oidar
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.
pncnmnp
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.

voxl
LanguageTool is free and open source.
pncnmnp
This is certainly an interesting tool. Also, it seems that they offer a great API - https://languagetool.org/http-api/.

However, it appears that the self-hosting option only gives access to the basic version (https://news.ycombinator.com/item?id=32238705), which is still impressive, but the premium version supposedly has better grammar and style features.

Honestly, ChatGPT's $0.002 per 1k tokens is quite tempting for me. Even after hundreds of queries, my monthly usage is less than 50 cents.

simonw
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 paste TSV values into to preview that data as a table recently, one prompt produced exactly the prototype I wanted: https://github.com/simonw/datasette-paste-table/issues/1

I use it for brainstorming. "Give me 40 ideas for Datasette plugins involving AI" - asking for 40 ideas means that even if the first ten are generic and obvious there will be some interesting ones further down the list.

I used it to generate an OpenAPI schema when I wrote my first ChatGPT plugin, see prompt in https://simonwillison.net/2023/Mar/24/datasette-chatgpt-plug...

It's fantastic for explaining code that I don't understand: just paste it in and it will break down what it's doing, then I can ask follow up questions about specific syntax to get further deeper explanations.

Similar to that, I use it for jargon all the time. I'll even paste in a tweet and say "what did this mean by X?" and it will tell me. It's great for decoding abstracts from academic papers.

It's good for discovering command line tools - it taught me about the macOS "sips" tool a few weeks ago: https://til.simonwillison.net/macos/sips

kzardar
How often do you find yourself decoding abstracts?
pubby
I tried out the wxWidgets library recently and used GPT to generate examples on how to do things. Thought it worked excellently and got 99% of the code right.

In the past, I'd have used forums to find examples. There were still some forum posts about wxWidgets on Google, but I got the impression they were hiding most. Either way, GPT had them on demand.

ActorNightly
It's a very good doc search. if you are working with new systems, it's insanely efficient for learning
spcebar
I was trying to figure out what an uncommented piece of code left by an old vendor actually did and so I asked ChatGPT. It instantly took me line by line through the code and saved me probably 10 to 15 minutes.
JoshMandel
Lots of tasks that I understand, but where I'm not familiar enough with the details to be productive. Anything that's easier for me to read than to write. Anything where I'd otherwise be stumbling around trying to build a template for myself.

Here's an example capturing a session from earlier this week:

https://twitter.com/JoshCMandel/status/1638723030154203138

jmann99999
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 to edit it but generally it is pretty close.

zzleeper
Can you provide an example of what prompts would you use?
jmann99999
Here is a good example:

1) Use Chat GPT in GPT-4 mode. I have found GPT-3 doesn't work in the same way.

2) I ask "What APIs does EasyPost have?"

It will respond with 7+ API endpoints

3) I ask "Can you write code in Ruby for the rates API?"

It responds almost perfectly with workable code from my experience in Ruby.

4) Then I ask "Can you give me that in Elixir?"

It responds with something I think is about 90% right. I am not as familiar with it but it seems close.

I am not trying to replace myself... I am just trying to make my job easier. And this seems to do it.

jmann99999
Note: I tried with GPT-3.5 and it doesn't respond with all the same APIs available. That said, if you want to try the above... It appears that the rates api isn't available in 3.5 but if you follow the example through.... it will still produce nearly identical code for the rates API even though it doesn't say that it is there.
axlee
please send your inputs. cute stories are whatever.
nathanmcrae
This is exactly the kind of thing I hope LLM chatbots will be genuinely useful for. Though, how often do you find it completely hallucinating endpoints / parameters etc. ?
javajosh
I use it for similar things as GP, and find its strengths to be similar too.

ChatGPT hallucinates SVG path attributes. Ask it to make an svg of a unicorn - it will give you markup that looks okay, but if you look at the values of the paths, it's clearly gibberish.

(SVG is a particularly interesting case because it's XML on the outside, but several attributes are highly structured, esp g.transform and path.d. Path.d is basically the string of a Logo-like programming language. I was specifically looking at these attributes for realism, and didn't find it.)

dr_dshiv
3.5 or 4?
sho_hn
Same experience for me with 4. It doesn't seem to have the ability to conceive of something visual and map it to SVG at the moment, or only extremely rudimentary.
jmann99999
Great question. If you ask it for an API endpoint that is described online but isn't well documented publicly, it seems to default back to what it thinks you should do. For example, in one example, it hallucinates that you need a bearer token.

I don't know whether that is because that is a common way of doing things or whether a previous prompt responded with a bearer token... But it wasn't right.

For me, it's a leaping off point that often saves time if I ask the right question. To your point, you have to be quick to know enough about the API to deduce whether you and Chat GPT are in the same universe.

DoingIsLearning
> 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.

teaearlgraycold
Get ready for ChatGPT: Enterprise edition! Now with SOC 2 compliance!
di456
A couple more years of chip improvements and it may run self contained within a device.
jmann99999
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.

unixhero
They already are. It is 99% stored on a Sharepoint on a Teams site anyways
neoncontrails
What does this mean? I'm unfamiliar with Teams, the only person I know who uses it is my partner who works for the government (non-technically).
baq
It means quite literally what it says - if you have office 365 you most likely have all your data in the MS cloud sharepoint. MS also has a separate government cloud.
johnwalkr
Not only do you likely have access to all the other Microsoft stuff if your company is using teams, teams uses sharepoint for file sharing. If you use only teams for 2 years and one day login to office365.com, you’ll probably be surprised with the main screen that shows the files you’ve shared (without context, they’re just sitting there) and you’ll probably also be able to see what files your colleagues are sharing and working on.
plagiarist
I think companies are fine with sending confidential data to Microsoft (Office, GitHub, Azure...). It's just so far unclear with ChatGPT if that data can come back out. It has apparently already leaked some user queries, so that was a very reasonable concern.

If they put it in Office and guarantee siloing information the legal departments will just have a regular contract to review and approve.

_nalply
This is one of the causes there's a push to run your own engines for large language models: if you run your own service you can control the environment, data and reproducibility.
bennysonething
This is exactly what my employer is doing, they pay so that our internal data (from employee queries) does not become part of the model. They've blocked the public chat gpt etc.
euroderf
All your topics of interest are belong to us.
jerrygoyal
> Generally rewriting emails for clarity

I built a free ChatGPT chrome extension that integrates with Gmail for better UX: https://chatgptwriter.ai (300k users so far)

quickthrower2
300k users is insane. Is it BYO key? Otherwise how do you handle that much load for free?
theonlybutlet
Looks like it's scraping the chatbot? You have to login to your chatGPT account?
ryann_wisc
Great extension! I used it recently, and had some trouble drafting email reminders (to respond to an email). Do you have any tips on how I could do that with the extension?
avereveard
chatgpt isn't compliant with any regulation including gdpr how much private data are your extension's user sending there?
themodelplumber
You reminded me: I discovered that ChatGPT had invented an API for me. Has that happened to you yet?

Since it went to the trouble of writing code for the API as well, I contacted the API developers to follow up about the topic. The code given was kind of a hand-wave anyway so I'd need to polish it up.

The developers were surprised to hear they had an API. In truth, there was no such thing.

I then found myself in one of those awkward "welp, guess I can keep my job" conversations...good for them, but for me: Go home, no API here. A disappointment with some meta-commentary sprinkled on top.

pishpash
That's just asking for their API to be implemented by some bot. Not sure they really get to keep their job.
ornornor
I asked it to `curl` my homepage and pretend to be a terminal, only executing the command and showing the output.

It got the format etc right but the actual content was completely hallucinated.

schappim
This has improved significantly between 3, 3.5 and now 4. It used to create a lot of Apple Frameworks/Classes and Methods, many of which would have been useful if they actually existed.
ElCapitanMarkla
Yeah I was coding up a fairly complicated payment form for a Stripe like processor the other day. I thought I’d give chatgpt a go and it confidently gave me the example code I needed and told me how to use it, etc. I was blown away until about 30 seconds later when I realised it was all complete bull crap. It was quite bizarre because this company didn’t really have any public docs out from when chatgpt supposedly harvested it’s data until, but it knew about the company and knew a couple of funny keywords this company uses in its form, so it was almost believable.
ElCapitanMarkla
One shining use case though, I typically live in Ruby and the example code for this company was all Java and Python. Getting ChatGPT to convert the boring encryption methods into Ruby was amazing.
qrio2
yeah even asking for common node library/sdk implementations has been off for me, calling functions with options that are not accepted, or what it thinks they should be
VoodooJuJu
Could you mock-up what might be a typical email written by you, then pass it through GPT, then post both responses here? I'd be curious to see what the difference looks like for someone else's writing. I've tried this exact use-case and noticed a drop in quality and clarity, rather than an improvement.
abledon
I use it to write tons of boilerplate code in random flavour of the week languages I am dealing with at work or on hobby projects. e.g. nginx/ansible/powershell/golang etc.. weird codebases your thrown back into a few years later. I know what I want, I just forget the exact syntax of how to get it done. Sometimes its wrong and I have to correct it, but half of the battle is knowing when its bullshitting.
bassrattle
I ask it for functions in Google Sheets and it gives me the perfect thing I never would have come up with myself, sometimes functions a mile long. I also explained the Maps for Sheets and GPT for Sheets extensions, and it is a master of both.
JoshMandel
I find GPT very helpful for trying to understand the rationale behind decisions from a bit outside my field. These are cases that probably don't take any great insight for a practitioner, but which can be hard to arrive at for an outsider.

Being able to have a quick back and forth can keep me on track and productive instead of falling down a rabbit hole of research. An example might be this discussion with Bing from earlier today

https://docs.google.com/document/d/1jCZICl8wrsk8b5OTM9xpFbL5...

carbocation
I’m obligated to pick up a new bioinformatics DSL and have been asking GPT4 to translate my current code (bash, go, python) into this language. It is not perfect but it gets me close to what I need, with some editing.

Sometimes I ask it to make music: https://github.com/carbocation/jinglebells

aaronscott
It’s been really helpful for picking up a new programming language. Particularly around helping me understand conventions in a language I’m not familiar with.

GPT-4 has been great at breaking down complex regexes that I am too lazy to parse out in the moment.

I’m also finding it helpful as a creative partner on naming things. Something I feel like I spend a lot of time noodling on. Like: creative names for a data warehouse that are surfing related (BoardRoomData lol).

bassrattle
I use it to give me the perfect functions for any task I can dream up in Google Sheets. Some conplex functions seem like a novel I never would have made, but it works very well so quickly and when it errors, it nearly always can debug. It understands the Maps for Sheets extension well and I'm trying to teach it to master GPT for Sheets.
abdullahkhalids
My big question is, are people at OpenAI actively using GPT as part of their work? Are they getting a productivity boost because of it?
Cyphase
Yes, apparently.

> We’ve also been using GPT-4 internally, with great impact on functions like support, sales, content moderation, and programming. We also are using it to assist humans in evaluating AI outputs, starting the second phase in our alignment strategy.

Source: https://openai.com/research/gpt-4

maytc
I've been using it as an aid in my writing process. Essentially, I can now pour my thoughts onto paper, complete with errors and poor word choices. With just a click, GPT transforms it into a presentable version.

Basically I created a small app to streamline the workflow. https://henshu.ai

techtonicshift
This is cool. What kind of prompts are you running in the background to improve the prose? How can I direct the prose in a certain way - say if I wanted my text to be official or funny?

We are building a GPT integration as well that helps users analyze reviews. Check out our demo https://show.nnext.ai/

maytc
You can ask it to rewrite the given prose and make it funnier. If the given text is already kinda funny it should spice it up. If it doesnt have much material, gpt may likely hallucinate some material to get it to be funny
Mavvie
I've mostly been using it to write shell scripts, or to answer specific/hard to Google questions about various libraries/tools.

Sometimes I use it to help me come up with names for projects/classes, sometimes I use it for debugging help (X doesn't work, why not?)

I think I could get a lot more out of it if I was more creative. It's an incredibly valuable tool already (on a similar level as intellij for me)

SomewhatLikely
One off extractions from semi structured text like an email or paragraphs from a webpage. Sure, I could spend 40 seconds coming up with a regex that I run to reformat how I want it, or I can just say it in plain terms. And if I need something a little more involved it has my back too: "Extract the domains from these urls as one column and give a user friendly name for the website in the second column and give a short description of what the purpose of the site is in the third column"
why5s
Various things:

- Non-technical explanations. Useful for the pointy-haired boss. And his boss as well.

- Stack Overflow (but on steroids).

- Summarizing long-form articles my friends send me.

- Generating rudimentary programs/scripts I'm too lazy to write on my own.

- Tutorial-style resources for unfamiliar technology (like writing CRDs in k8s).

- Generated a working Makefile.

- Sometimes, I'll take existing small programs in Go and have them rewritten in another language. It's just fucking cool to watch.

- Rudimentary translations from English to French.

Can't use CoPilot for work yet since, well, they can (and will) upload proprietary IP. But for everything else in life, the productivity gain has been enormous.

brainthrowaway8
I've asked GPT-4 about the human brain and specific metabolic pathways every day so far. If you ask it for answers in jargon like written in a textbook or a journal it will provide an obscene level of detail that you can then verify.

As a "domain specific words" generator for building up a glossary, it can't be beat. From a prompt perspective I have to tell it that we are both world class neuroscientists but it knows more about this specific question than i do. Then I tell it to reply using correct jargon for the domain like that written in a textbook

nwatson
I've been a paying ChatGPT subscriber for about three or four weeks now. One day I had a few thorny work issues, asked the free version, and it was so good I got a subscription.

Since then I've asked some about general knowledge, history, religion, geography, politics, other topics of interest. Mostly in English, but some in Portuguese and a little in Spanish. It's extremely good in all three languages.

Mostly though I've been asking about random work topics that come up every day. We use a lot of lots of systems, tools at work, and I need to write software to handle diverse areas. ChatGPT cuts right to what I need as far as: (a) general knowledge of tools and what their purpose is; (b) surveys of categories of tools, comparisons between competing offerings; (c) specifics on how to use, configure, program against various tools, query data, change things; (d) questions on best practices and pitfalls. This is mostly in context of macOS, Linux, AWS, kubernetes, observability tools, and APIs for lots of DevOps-related systems. I do lots of coding in Python, I also do a lot of ad-hoc diagnosis of situations. (We have a great DevOps team that manages infrastructure with standard DevOps tools -- my job is to build what those tools don't address so well, and also to help build out future data-engineering efforts.)

I'd say my use of Google search to find relevant articles / pages has gone down 70%. One small example today, I wanted to use `jq` to process some `docker ... --format json` output to pull out some data. I don't want to learn the ins and outs of `jq`, I described my problem and it gave me a good template I could adapt.

Any time now in scrum or other meetings, if there's any question about something, we often just consult ChatGPT during our Zoom/screen-share sessions. I think generally I have a better sense on how to structure questions and question progressions to get quick answers than some others.

I've also found ChatGPT makes up stuff sometimes ... but it's usually close enough.

One comfort I have is that, at least for now, ChatGPT can't direct the overall organization of code for the many situations I need to address, so I'll have a job for a while. It does though fill in the knowledge gap at the edges, I don't waste near as much time searching for and reading documentation and examples. ChatGPT usually has good ready-made low-level examples when I need them, and high-level descriptions of tradeoffs and best practices.

I'm "committed" to Jetbrains tools, been using them for a long time. Today I began wondering what I might be missing from CoPilot, downloaded the CoPilot plugin for PyCharm (would also work for IDEA, DataGrip, etc.). I couldn't get the CoPilot plugin to log into Github and saw that others have had similar problems in the past ... so I can't use CoPilot yet. Maybe in a week or two I'll have a basis for comparison. (I don't want to switch to VSCode.)

EDIT: word choice, minor clarifications

motoboi
I just asked it to summarize your comment:

Summary: - The user has been a paying ChatGPT subscriber for 3-4 weeks and has found it to be extremely helpful in resolving work-related issues. - ChatGPT has been helpful in providing general knowledge, surveys of categories of tools, specifics on how to use/configure/program against various tools, and advice on best practices and pitfalls. - The user mainly asks questions related to macOS, Linux, AWS, kubernetes, observability tools, and APIs for DevOps-related systems. - ChatGPT has reduced the user's reliance on Google search by 70%. - The user has found ChatGPT to be helpful in structuring questions and question progressions to get quick answers. - ChatGPT sometimes makes up stuff, but it's usually close enough. - The user is committed to Jetbrains tools but is exploring CoPilot and has downloaded the CoPilot plugin for PyCharm.