Claude's memory feature mocked: saves useless notes, ignores memory when it matters
kalomaze · x · 2026-11-13
kalomaze mocks the memory feature in Anthropic's models: the agent dutifully says "let me save this to my memory md file," but ignores memory exactly when listening to it would help, while injecting irrelevant historical failures in unrelated contexts. He wonders what tenobrus meant by "the models are good enough" regarding this feature. The thread highlights the gap between memory being written and memory actually being used at the right moments.
Related event: Developer complains AI agent memory fails when needed, intrudes otherwise(2 posts)→
More from coding & agent
- Dev open-sources first MCP server for Power BI custom visuals, seeks feedback — Constant_Plane4937 · 2026-11-13
- LLMs' mental map of SF tested: best street-level score 0.32 vs 0.23 random — Evening_Hawk_7470 · 2026-11-13
- Levels 9 and 10 of AI adoption: simulating strategies with competing agent organizations — danshipper · 2026-11-13
- Idea basins: why autonomous agents get stuck, and how frontier models explore differently — AlexGDimakis · 2026-11-13
- Cap, the open-source screen recorder, launches on iOS with instant share links — JosephJacks_ · 2026-11-13
- Why reasoning distillation fails on 9B models: six LoRAs, mixed results — SignificantZebra5883 · 2026-11-13