Your agent's memory can't tell a correction from a repeat

Building a drift-adaptive memory for a Qwen agent, and the one debugging session that turned a tie into a win. I built a memory sidecar for an LLM agent. The pitch was simple and, I thought, a little clever: decide what to remember with no LLM call at all. A small neural memory (Titans-style, trained at inference) produces a "surprise" score for every incoming fact. Novel things are surprising, so you store them. Repeats are not, so you skip them. Zero tokens on the write path, while systems…