built a memory pipeline on Qwen3 235B A22B Instruct 2507 that scored #1 on LongMemEval-S (470/500) while being ~10x more token efficient than the next best system
英文标题：built a memory pipeline on Qwen3 235B A22B Instruct 2507 that scored #1 on LongMemEval-S (470/500) while being ~10x more token efficient than the next best system
Over past ~10 months I've been iterating on my memory system so I can make a proper assistant, like Rick's garage from Rick and Morty. I benched my latest iteration and it scored top out of any system I know of (470/500 on LongMemEval-S), while being way more token efficient and cheaper. The e
中文
Over past ~10 months I've been iterating on my memory system so I can make a proper assistant, like Rick's garage from Rick and Morty. I benched my latest iteration and it scored top out of any system I know of (470/500 on LongMemEval-S), while being way more token efficient and cheaper. The e
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Over past ~10 months I've been iterating on my memory system so I can make a proper assistant, like Rick's garage from Rick and Morty. I benched my latest iteration and it scored top out of any system I know of (470/500 on LongMemEval-S), while being way more token efficient and cheaper. The e