I don't. My productivity is just fine with bash<p>To empower thinking in this information overload era, turn off your computer and start writing on paper
None, because I am not a productivity-obsessed drone. From what I've tried, Github Copilot is pretty good, but it's often more disruptive than helpful, therefore I do not use it on a daily basis.
ChatGPT and GitHub copilot have changed my life. I ask ChatGPT what's the next domain/area that is ripe for disruption. ChatGPT is very smart, it replies instantly. I then instruct copilot to go code me a MVP for this chosen area. Copilot isnt as fast as ChatGPT, but it does deliver. By the time I go out, watch some movies, then take a walk on the beach and am back, the MVP is ready and I unleash it on VCs who shower me with money. And now with the newly introduced FedNow money transfer facility, I get the money instantly.<p>Before ChatGPT and copilot, I could hardly go out for movies during the day. And beach? Only during weekends :(
ChatGPT (4) is great to get ideas for programming problems. As far as actual usable code, it's hit and miss, usually not quite right. But especially for things like CSS or anything I have not used much, it definitely helps me at least get started or explore approaches to problems.<p>I put something like "tree of thoughts" in my Custom Instructions setting and now it holds little meetings with itself before finalizing code suggestions. Don't have the prompt on my phone but search for "Lucidate tree of thoughts" on YouTube and then modify that slightly for software engineering.
None.<p>And my reasoning could be a strange one. My knowledge of mathematics (esp. probability and statistics) and algorithms, and my memory used to be pretty sharp. I could retain a lot of information, and perform fast manual calculations using log book. All that started to deteriorate when I started relying on search engines for everything. No doubt it was convenient, but I lost touch with foundational concepts. My memory and speed are not what they used to be.<p>So as long as I can. I’m going to keep co-pilots and ai/tools at bay.
"I don't." Gotta make sure we know how cool and trend-bucking you are in a thread asking those who do use them. It's like going into a Mac thread and letting us know you don't use Apple stuff. That super neato for you, but it's not particularly helpful.
I use all three major AI platforms daily for content classification, summarization and generation. In a similar vein as “X company uses AI to write content and fires writers”. Except I’m the writer. And there’s two of us. And we never had other writers so no one’s getting fired. And if our project takes off we will have to hire more.<p>Writing and rewriting and re-targeting and ideation are very much helped by AI.<p>That said, the plethora of AI baked tooling isn’t that helpful yet. Wrappers around the APIs are helpful… most of the other apps that promise more are pretty bad and make AI look bad.<p>Tools that help manage prompts and iterate on those have been most helpful.<p>The one I use the most is Text Generator in Obsidian.
I don't.<p>There's nothing for my job that I can use it for. I am a programmer. I have been doing it for over a decade now. The majority of my job is spent in existing codebases. So, using ChatGPT or copilot actually gets in my way. Most of the time the job is simple enough I don't need it. It's more of an exercise is not letting boredom win. When it's more complicated I still don't need it because the structure and purpose of the code, how it fits into the existing code, and what exactly I want it to do is something ChatGPT can't help me with. At my experience level syntax, algorithms, and patterns are stored in the L1 cache I call my brain. When I need a reminder of something obscure its <i>still</i> faster for me to grok documents (because I know where to look) than it is to ask ChatGPT for a contrived example.<p>It might be nice for generating boilerplate or helping a junior developer get up to speed faster. I won't pay for any AI tools. There has been no situation so far where I've had to scratch my head for so long that it would've been easier to do with ChatGPT. Unfortunately, the life of a programmer is mostly boring with short periods of absolute chaos. Honestly, I wish I had a job that created interesting hard problems where ChatGPT meaningfully contributes to my work.
I was having a discussion with ChatGPT about development difficulties in a micro services architecture. It helped me arrive at a possible improvement using dependency injection functions like get_sentry and get_mongo that can return a MagicMock instance of the respective runtime dependency by checking a RUN_MODE environment variable. The idea solves an immediate need to allow me to bootstrap the application to a minimum functional state in a CI or pre-commit environment. We can also expand on the idea by defining RUN_MODE behaviours for development, staging, and production environments with various gRPC stubs and service mocks in some environments.<p>I’ve also had a great experience using ChatGPT and GitHub Copilot assist me in writing unit tests for a Dango/WagtailCMS website project. ChatGPT particularly knows some subtle nuances of the Django and Wagtail APIs. It has been like having a personal tutor. Copilot then picks up on unit test patterns to write tests based on comment prompts or function names. In some cases, Copilot is suggesting test cases that I didn’t even think of simply by pausing my cursor on a blank line.<p>I’ve been live streaming my open source development using these tools, in case anyone would like to see how they are making me a better developer.<p><a href="https://youtube.com/@brylie">https://youtube.com/@brylie</a>
I use aider[1], python tool for coding after learning about it from the author that posted it on here some months ago. It works well in the design phase and early parts of projects. Lately I haven’t been using it as much, unfortunately, because I have been working heavily on a library that was released after 2021 and it’s not as immediately helpful a lot of the time.<p><a href="https://github.com/paul-gauthier/aider">https://github.com/paul-gauthier/aider</a>
GPT-4 via ChatGPT, mostly for coding and GPT-4 via <a href="https://flowch.ai" rel="nofollow noreferrer">https://flowch.ai</a> (our tool) for anything that involves my own data (including my own code), or where I want automation, such as running a prompt on many pieces of data.<p>Overall this has at least 5x my productivity, possibly 10x.
I was using Github Copilot, however I just ended my subscription because I wasn't using it enough despite being elbow deep in code every day. Most of the time the integrations that I use (JetBrains Rider and VS Code) wouldn't function correctly or I'd constantly be logged out. When the integrations _were_ working, the suggestions would be decent but occasionally when doing something like converting jquery to vanilla javascript I'd end up spending more time debugging the result of the suggestion than if I had just done the conversion myself.<p>Otherwise, I use ChatGPT to help me write tickets/user stories for work as well as for generating test cases for my QA engineers to follow.
After trying many other tools on Windows, I found them either too bloated or too rigid. So instead, I built my own tool using AutoHotkey. The end result is a single binary that's less than 1MB in size. I can define my own prompts in a simple INI file and invoke those prompts anywhere.<p><a href="https://github.com/overflowy/chat-key">https://github.com/overflowy/chat-key</a>
CodiumAI [0], helps me generate meaningful test suites and code suggestions.
This is exactly what I need to enable me to code fast <i>with</i> confidence.
Really, just try it, and let me know if you are not positively surprised.
[0] <a href="https://codium.ai/" rel="nofollow noreferrer">https://codium.ai/</a>
None. I tried many including GitHub Copilot.<p>I think these tools are not there yet, mostly because they’re simply producing wrong/non-compilabe code way too often.<p>I see a potential in creating modern AI-supported plugins targeting specific software development areas like test code generation, auto code review etc. though.
I use Chat GPT basically in lieu of google for programming questions now, with the caveat that you need to check its work. It's good at skimming through documentation, but I don't trust it to really write code. For newer things I use bing chat since it has access to more current information.
The AI tool that I currently use the most is ChatGPT, which helps me systematically organize complex results from multiple Google searches. Much of my work involves text editing, so I am truly looking forward to an AI all-in-one reading and writing tool.
I actually use the OpenAI playground most of the time, both for coding and for asking questions. It's a bit less chatty without me having to engineer the prompt as much. It also allows me to edit assistant responses so that future prompts are based on corrections.
I'm using Finito, which is like ChatGPT available anywhere in the OS.
<a href="https://www.finito.ai/" rel="nofollow noreferrer">https://www.finito.ai/</a>
<a href="https://hal9.com" rel="nofollow noreferrer">https://hal9.com</a> for data analytics with generative AI, free when using CSV files.
I am not going to renew my GitHub CoPilot as ChatGPT subscription delivers more value. I am probably going to write a VSCode plugin for my specific environment.