3.7 Thinking Model's Code Quality Needs Urgent Improvement

[normalnormie]

@CosPie You’re a long-time Cursor user but joined 10h ago, the exact time of your post.. I’ve got the opposite “problem”, it always read rules and sometimes I need to tell it not to, you may have problems with your descriptions as its needed a good description and takes time to enhance, also my rules are in xml to further follow and verify each step, take my description for python guidelines which always works:
Python Style Guide, MUST activate when interacting with python code.
Add this to your rules for AI:

@raythurnvoid

⚠️ FETCH RULES OR YOUR RESPONSE WILL BE WRONG ⚠️

MANDATORY: CALL fetch_rules FIRST

- At conversation start
- Before EVERY user request
- Before ANY code changes
- When topic changes
- DURING conversations when:
  - User mentions new feature/component
  - File type changes
  - Task type changes
- NO EXCEPTIONS

CHECK ALL MATCHING RULES:

- General guidelines (ALWAYS)
- Feature rules
- File type rules (.ts, .css, etc)

RULES OVERRIDE YOUR KNOWLEDGE.
PROCEED ONLY AFTER APPLYING ALL RULES.

REMEMBER: EVEN MID-CONVERSATION, FETCH RULES AGAIN!

@drahn “never” contradicts “update” instruction, ask AI to refine your rules