Skip Navigation

Posts
5
Comments
86
Joined
3 yr. ago

  • I use Copilot, but dislike it for coding. The "place a comment and Copilot will fill it in" barely works, and is mostly annoying. It works for common stuff like "// write a function to invert a string" that you'd see in demos, that are just common functions you'd otherwise copypaste from StackOverflow. But otherwise it doesn't really understand when you want to modify something. I've already turned that feature off

    The chat is semi-decent, but the "it understands the entire file you have open" concept also only just works half of time, and so the other half it responds with something irrelevant because it didn't get your question based on the code / method it didn't receive.

    I opted to just use the OpenAI API, and I created a slack bot that I can chat with (In a slack thread it works the same as in a "ChatGPT context window", new messages in the main window are new chat contexts) - So far that still works best for me.

    You can create specific slash-commands if you like that preface questions, like "/askcsharp" in slack would preface it with something like "You are an assistant that provides C# based answers. Use var for variables, xunit and fluentassertions for tests"

    If you want to be really fancy you can even just vectorize your codebase, store it in Pinecone or PGVector, and have an "entire codebase aware AI"

    It takes a bit of time to custom build something, but these AIs are basically tools. And a custom build tool for your specific purpose is probably going to outperform a generic version

  • The forks could just change their name, so they're more easily found. For example mRemote got pretty much abandoned, so mRemoteNG got created.

    Or people give forks better names. For example, I've forked some dotnet6 project, and called the fork {project}-dotnet8 - then when people look thought the fork list on github, it's not 20 forks all with the same name

  • Personally I don't have any problems with it (if that was directed at me) - I've added 418 as "unhandled exception code" response to a bunch of applications, so I can easily differentiate whether my application is throwing an error, or whether it's some middleware gateway AWS io-thing

    I was just curious what OP thought about it, since in the early days it wasn't uncommon to add goofs or easter-eggs into software, but nowadays not done so much... and apparently the "HTTP Working Group" doesn't like it either... So I was curious whether OP though in hindsight whether it should've been added or not