Hey, thanks for the report. This is a known limitation. LLMs follow rules in a probabilistic way, and as a chat gets longer, earlier context, including rules, gets less “weight” in the model’s attention.
A couple things that help a lot:
-
Rephrase “negative” rules into “positive” ones. @nedcodes is right. Instead of “NEVER use the
gocommand”, try “ALWAYS use/path/to/gofor all Go build, run, and test commands.” Positive wording tends to stick better over multiple turns. -
Keep rules short and specific. If your rules file has lots of instructions, split them into separate, narrowly focused files. Fewer lines per rule usually means better compliance.
-
Reinforce during long sessions. For critical rules, a quick reminder in your prompt like “don’t forget to use
/path/to/go” often helps after 3 to 4 turns. -
Start new chats for new tasks. The context window is limited, and after many iterations the model can lose the thread. Fresh chats mean the rules get full attention again.
Related thread with more tips: Cursor often forgets .mdc instructions (Cursor often forgets .mdc instructions)
The team is aware of the rule-following issue. There isn’t a guaranteed fix since this comes from how LLMs process instructions. Let me know if the rewording helps.