Constant formatting problems with GPT 4.1

[troehrkasse]

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Chat responses are frequently malformed, with parts of the AI’s response getting sucked into a code block, and then re-stated after the code block. Makes output confusing and cluttered and difficult to work with.

Steps to Reproduce

Chat with GPT 4.1
Observe messy responses

Expected Behavior

Output should be formatted correctly

Screenshots / Screen Recordings

Operating System

MacOS

Current Cursor Version (Menu → About Cursor → Copy)

Version: 1.7.46 (Universal)
VSCode Version: 1.99.3
Commit: b9e5948c1ad20443a5cecba6b84a3c9b99d62580
Date: 2025-10-14T01:21:46.830Z
Electron: 34.5.8
Chromium: 132.0.6834.210
Node.js: 20.19.1
V8: 13.2.152.41-electron.0
OS: Darwin arm64 25.0.0

For AI issues: which model did you use?

GPT 4.1

Additional Information

Happening on all requests across different repositories.

Does this stop you from using Cursor

No - Cursor works, but with this issue

[deanrie]

Hey, thanks for the report. The formatting issue where text gets duplicated inside and after code blocks isn’t expected behavior. It’s a long‑standing bug that we’ve already fixed.

To help narrow it down, please check:

• Does it also happen with other models (e.g., Claude 4.5 Sonnet)?
• If you export the chat (click the three dots in the top‑right of the chat → Export Chat), does the raw markdown show the duplication, or is it only a rendering issue?

This will help us see whether it’s specific to GPT‑4.1 output or a broader formatting/rendering problem.

[troehrkasse]

Thanks for getting back to me. It does not appear to be happening with other models, I just tried a request with GPT-5 and it formatted correctly.

The problem seems to be even worse today for 4.1, here is a new chat I just started. Everything just in one huge run-on bold bullet point:

I tried exporting this chat, and it looks fine in the MD file:

[deanrie]

Thanks for the info, that’s very helpful.