Increasing problems with ChatGPT 5.2 in Code Spaces #185417
Replies: 1 comment
-
|
💬 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.
Uh oh!
There was an error while loading. Please reload this page.
-
Select Topic Area
Bug
Body
When working in spaces - the shared files in the space has always been easily available to whichever LLM model I've chosen.
But recently, ie - past month - it's become more and more tedious.
I keep getting the following replies whenever I work with files that are more than 50+ lines of code / markup:
When I tell it to pull code from the repo directly, it will usually do so - but needs to be prompted to perform the operation. It doesn't assume the data is invalid if it's garbled / stripped - so I need to either tell it to re-pull or give it an OK for it to re-read the file from the repository.
This makes it very difficult to work with LLMs in code spaces as I constantly need to assume it's not seeing the full picture and have to verify end of code snippets etc.
Beta Was this translation helpful? Give feedback.
All reactions