News for hackers. Stuff that matters.
Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ... by woah on Wednesday March 19, 2025 @11:20PM (#43419638)
Strange to read this and the parent comment, since Cursor has never made a single error applying patches for me. The closest it's come is when the coding model adds unnecessary changes which of course is a completely different thing.
Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ... by logicchains on Thursday March 20, 2025 @02:56AM (#43420399)
Which model are you using with Cursor?
Re:AI Blindspots – Blindspots in LLMs I've noticed while AI ... by woah on Thursday March 20, 2025 @01:35PM (#43426276)
Usually Claude 3.5, but I believe they have a separate application model which puts the code that the bigger model suggests into the file