I trialed GitHub Copilot and used ChatGPT for a bit, but recently I found myself using them less and less.
I’ve found them valuable when doing something new(at least to me), but for most of my day-to-day it seems to have lost it’s luster.
I was skeptical at first, but after using phind.com it partially changed my opinion on using AI for development assistance.
It massively helps me to filter out information and leads me to the right answer.
Like the other day, I searched on how to write some Latex symbols or how to use Java Stream API, it spit out the result immediately that saved my precious time on searching the Internet.
I don’t use CoPilot though.
I don’t have Copilot and never plan to use it. I tried Tabnine back when it was early and found it broke my flow more than helped. And I don’t have the patience to try either again… I’m too reliant on muscle memory and key bindings to have these tools get in the way.
As for ChatGPT, my company has a decently-restrictive policy. We can and are encouraged to use it, but no IP can be given. So everything is really generic. That said, I find it most useful in two areas. First, getting me unstuck. And what I mean by that is, I basically ask it if it’s possible to solve a problem. If it spits out code, I’ve got a general idea of how to get there. In short, I skip Stackoverflow.
Second, I like it for a second perspective. For example, I recently had a task to remove “duplicate rows” from a database table. We’ve used the same algorithm 2 or 3 times prior. Something wasn’t sitting quite right with a reviewer of the changes I made for this particular need, but even after group discussion, no one could put a finger on it.
So, I asked ChatGPT how to do this same thing and its solution was actually sound. We still kept my solution… and eventually figured out what was wrong, after the migrator didn’t do its job properly. That resulted in a good, solid day of hand-fixing databases… I really should have listened to my gut when ChatGPT gave a totally different, probably more bulletproof answer. It may not always correctly, but that doesn’t mean it’s not necessarily helpful.
I’m a FSE and I use GitHub copilot and Perplexity. I wouldn’t want to code without them anymore.
I want to get things done (especially when I’m at work) and not spent time reading docs or having 20 tabs of stackflow open. I’ve had enough of that lol.
I think everyone here knows copilot but perplexity is a lot smaller and newer. It’s basically like chatgpt but faster and it googles stuff, giving sources for each claim that I can read for myself.
For example, for my latest project I decided to give tailwind a try and instead of having to look through the docs for every little thing I just ask perplexity and it sums it up for me, even giving examples.
And I use copilot a lot for mundane tasks, for example when I write an API that takes an object of type Foo, Copilot auto Fills making variables and checking each for nulls and then I use that API in the frontend copilot already knows what I’m about to do and auto-fills the fetch.
I use https://labs.kagi.com/fastgpt once or twice a week when I need a quick answer about a very obscure subject that is mentioned only once on the internet. It’s free as I’m a Kagi subscriber, and I usually get interesting results. But I don’t copy-paste code, it’s stupid.
They’re very useful for the boilerplate stuff and it’s somewhat rewarding to type out 3-4 letters, hit tab and wind up with half a dozen lines in a bash script or config file.
They tend to get in the way more for complicated tasks, but I have learned to use them as a psychology trick: if I have writer’s block, I just let them pump out something wrong since it’s easier to critique a blob of text than a blank page.
I use ChatGPT with GPT-4 as a search engine when a Google search doesn’t immediately turn up the answer I’m looking for. ChatGPT won’t necessarily give me the right answer either (though sometimes it does), but reading its answers almost always causes me to think of a better search query to plug into Google. That doesn’t sound like much but it can save a lot of time compared to stumbling around trying to figure out the right keywords.
Occasionally I ask ChatGPT to write code samples, but (though they’re way better than GPT-3.5) they still hallucinate a bit too much, e.g., inventing library functions that don’t exist or, worse, inventing plausible-sounding but wrong facts about the problem domain. For example, I recently asked it to write some sample code to work with geographic data where the coordinate system could be customized, and it invented a heuristic about coordinate system identifiers that is true most of the time but has a ton of exceptions. If I didn’t already know better, I might have tried it out, seen that it appeared to work on a simple happy-path example, and accepted it without knowing it was going to break on a bunch of real-world data.
Every once in a while I give Copilot another shot, but so far, I’ve always ended up turning it off after realizing that I’m spending more time double-checking and fixing its code than it would have taken me to write the code by hand. To be fair, I’m usually working on backend code in a language that doesn’t have nearly as much training data as some other languages. Maybe if I were writing, say, Node.js code, it would do better.
I use ChatGPT (with GPT-4) all the time for coding. I’ve developed a feel for the maximum complexity it can handle and I break down bigger problems into smaller subtasks and ask it to write code for them (usually one function at a time, after a detailed explanation of the context in the beginning). I need to review and test everything it produces thoroughly but it’s worth it. Sometimes it helps me complete tasks that would have otherwise taken a day to complete in 1-2 hours.
I also have Copilot installed but it isn’t as useful as ChatGPT. It’s nice to get a smart completion sometimes. I’m even in the Copilot Chat beta which uses GPT-4 and I find it inferior to ChatGPT with GPT-4.
I never touch GPT-3.5 anymore. It hallucinates too much and the quality of the output is very unpredictable. I guess most people who say AI is useless for coding haven’t tried GPT-4 yet.
Oh, and something else. In my experience, the quality of the output depends a LOT on the prompt. If you give a clear, detailed description of the problem, and try to express your intent instead of the specifics of the implementation, it usually performs very well. I’ve seen some people at work write the worst, sloppiest prompts and then complain how useless ChatGPT was.
This is really useful info, can you recommend a tutorial that you feel shows how to effectively use these tools along with traditional style coding? Or would you say it’s just a try and see approach/learn as you go. Personally, I think your comment best demonstrates where we are right now with AI assisted development.
Unfortunately the tutorials out there are mostly terrible. I’ve learnt it by experimenting a lot and seeing what worked for me. Some general advice:
- Subscribe to both Copilot and ChatGPT Plus and try using them as much as possible for at least a month. Some people prefer the former, others the latter, and you can’t know in advance which.
- Always use the GPT-4 model in ChatGPT but keep in mind that there is a 25 answers/3 hours rate limit. So try to squeeze as many questions and information into your messages as possible. GPT-4 is miles ahead of any other publicly available LLM, including GPT-3.5.
- Tips for ChatGPT:
- Give detailed, well-written prompts. Try to describe the problem the same way you would to a coworker.
- After describing the problem, ask ChatGPT if it needs any additional information to implement the code well. It usually asks very insightful questions.
- Answer the questions and then ask it to break down the problem into individual functions and then, in separate messages, ask it to implement them one by one.
- Remember that the context window is limited, after some time it won’t remember the beginning of the conversation so it’s worth repeating parts of the specification later.
- Tips for Copilot:
- Write the method signature and have Copilot implement it for you
- Write a comment and have Copilot implement the corresponding code
- Paste the code as a comment in a different language, write “the same logic in $lang2” in a comment, and it will translate it from $lang1 into $lang2.
I don’t use it that much for programming in the project directly, but sometimes to ask for input about ideas I have and pros/cons and follow up questions.
But just this week I used ChatGPT to help me write some git hooks I didn’t know were possible.
I use Copilot with IntelliJ (for golang) - which works fantastic, maybe because the language is simple and well-documented. I also use Copilot for Xcode (you can find this plugin on GitHub) with Swift/SwiftUI - it is so-so, Swift and SwiftUI evolve so much, so I don’t see a lot of benefits from using Copilot with Swift. And yes, I use a lot of ChatGPT (with typing mind wrapper). I mostly used GPT-4 model but switched to GPT-3.5 as they both can hallucinate, but GPT-3.5 can give me an answer quicker. Yes, they both can provide inaccurate answers, but I don’t ask them to write code that I am ready to put in my app, but primarily examples.
Copilot is still very useful for boilerplate, but ChatGPT is usually always wrong so it is faster to do it myself
I still have copilot on but I find it not really useful beyond very simple things. It is a smarter autocomplete, so it’s nice. But you always need to have your brain turned on because it definitely invents things.
It’s also sometimes entertaining when it makes things up. I especially enjoy when it makes up entries in the changelog.
As for ChatGPT, I use it occasionally mostly for tedious things I don’t want to spend time on. But I’ve definitely used it less lately. The hyper has faded.
Doing web-dev it’s not uncommon for me to run into libraries with poor documentation or missing examples. I could spend a lot of time trying to find the official docs, read through pages, not really find what I’m looking for, go to stackoverflow, maybe find something better maybe not. Now my first step is just asking ChatGPT my question. More often than not it gives me a working example, I get an answer faster than it would take to navigate official docs, and I can immediately get answers to followup questions or ask it to modify the example to be closer to what I actually need for my application.
I just don’t trust these tools to write code as efficiently as I can, knowing they are just backed by LLMs. If I have to spend my time vetting what they spit out to ensure correctness, efficiency, security, etc, then I might as well just do it myself from the beginning. I’m sure some find these tools useful and timesaving, but they’re not for me.
I find ChatGPT more accessible and usable than GitHub Copilot. I did initially use Copilot when it was first released, but I found myself being interrupted by the suggestions. There were times when it was useful, but it got in the way more often than not. I’ll concede that Copilot is really good at suggesting dummy data.
With ChatGPT I tend to explore a problem and a solution - it’s more of a purposeful back-and-forth. I will often ask for example code, but even if I use it, it will most often be re-written. The key thing here is that I am stepping out of my editor to interact with ChatGPT, and that works really well for me - I’m in a different thinking state, and I find this a very productive way to work.
ChatGPT 4 Helps me with better code, content ideas and mindstorming.
GitHub Copilot Speed up my writing since it can take context and give suggestions. I also have the Beta version with the chat but it is as good as ChatGPT 3.5 so i don’t use it.
Stable Diffusion I can’t draw so i use a lot of AI images, but mostly for placeholder.
Stable Dreamfusion Tried, did not get good results, don’t have enough vram.
NeRF Tried, haven’t use it more then a few test run, but will use it more in the future for when i make a 3D Game.
