Card #3134 · Cursor (AI IDE)
Degradation of Auto-mode quality and reliability
Long-time users are experiencing a significant drop in the quality of Auto-mode, citing poor context memory and failure to follow prompts. There is a perception that the product has become less reliable and more opaque regarding model routing and pricing, leading to a loss of trust.
Pain score
0.15/ 1.00 · weighted product of four components
Reach0.32distinct authors (log-normalized)
Recency1.00freshness decay, half-life months
Engagement0.28upvotes + comments, normalized
Monetization1.00willingness-to-pay cues in evidence
§ Evidence — 3 verified quotes
In the past 2 months, Cursor’s auto-mode has become about 50x worse. Context memory is horrible, adherence to rules is non-existant 60% of the time
Auto mode often feels like a black box that routes users to weaker models without enough transparency. The result is inconsistent quality, unreliable code edits, and a much lower sense of trust in the product.
I’m very disappointed to the tune of looking to terminate my annual subscription and move to other platforms.
Comments are a Pro feature — join the conversation, share what you've shipped, hear what others are building.
Upgrade to Pro