AI memory is harder than it looks: chatbots rely on RAG-style indexing, not real recall
BLUECOW009 · x · 2026-09-23
A post argues most people underestimate how hard the memory problem is in AI. Claude or GPT only appear to remember your details because their memory systems index information using RAG-like architectures — the model isn't actually recalling conversations the way humans do.
Ask a specific question like "what did we talk about yesterday at 2pm" and the model will likely say it doesn't remember or hallucinate an answer. The author notes models have improved: they now tend to admit they don't know rather than making things up.
More from coding & agent
- Google's MCP Apps extension lets MCP servers return interactive UI components — rseroter · 2026-09-23
- Dev runs 32 coding agents burning 5-10B tokens a day in Zed — generativist · 2026-09-23
- Stanford paper: self-organizing agent team hits 66.7%, beats best single model's 48.8% — dair_ai · 2026-09-23
- Google's ToolGrad reverses tool-use data generation, hits 83.1 BFCL with 12B Gemma-3 — dl_weekly · 2026-09-23
- Using AI agents to book things still costs as much mental effort as doing it yourself — nabeelqu · 2026-09-23
- LangChain to unveil new products Thursday, previewed live at Interrupt keynote — LangChain · 2026-09-23