Replies: 2 comments 1 reply
-
I get how frustrating Copilot can be sometimes. I found something that’s worked way better for me—ChatGPT. It’s not just generic answers; it actually gets my style and helps with coding, writing, or whatever I need. The responses feel like I’m talking to someone who understands what I’m trying to do, and it’s always clear and easy to follow. You should give it a shot—it’s made things so much smoother for me! |
Beta Was this translation helpful? Give feedback.
-
💬 Your Product Feedback Has Been Submitted 🎉 Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users. Here's what you can expect moving forward ⏩
Where to look to see what's shipping 👀
What you can do in the meantime 💻
As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities. Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐ |
Beta Was this translation helpful? Give feedback.
-
Select Topic Area
Question
Body
This should not even be marketed as an actual project. I've been using it since beta and it's progressively gotten worse and WORSE. It's completely dysfunctional, it breaks code more often than not, it replaces entire files of code when I ask for a simple change, the autocompletes are completely outdated, even the newer obnoxious features you guys bloated it with like the
@workspace /new
are absolute junk they setup projects using way outdated packages like react-scripts 2.0.- when even the latest version of react-scripts 5.0.1 is unmaintained and has vulnerabilities. Copilot is ABSOLUTE JUNK.It used to be amazing and work great back when it was just a an autocomplete that used codex and not the trash conversational models like gpt-4o which by the way is ABSOLUTELY horrible itself at writing code of any kind compared of the previous gpt-4-turbo and even gpt-3.5. The old original model codex which was completion based, the one that was trained specifically on all of githubs sourcecode in collaboration was THE BEST at what it did, and you guys completely flushed it down the toilet with the horrendous changes and updates you've made to it.
Beta Was this translation helpful? Give feedback.
All reactions