Parameters vs context memory

andrej-karpathy's two-memory-systems model: knowledge in a model's parameters is "vague recollection" — like something you read a month ago, quality proportional to training-data frequency (lossy-compression-of-the-internet) — while the context window is "working memory," directly accessible to attention.

Practical corollaries:

• Paste, don't recall — summarizing a chapter goes better with the chapter in the prompt than from the model's memory.
• Tools refresh working memory — web search exists to move facts from the world into context; that's the second hallucination mitigation after trained "I don't know" responses.
• The mechanism under smart-zone-dumb-zone: working memory is precious and finite, and matt-pocock's clear-don't-compact discipline is about keeping it deterministic. Karpathy names the same open problem from the research side: context windows alone won't scale to long multimodal tasks — some analog of "updating parameters while you sleep" (test-time training) is missing.

Hygiene corollary from How I use LLMs: start a new chat whenever you switch topic. Tokens in the window are "a precious resource": stale ones distract the model and make each next token slightly more expensive. Every tool (search, upload, interpreter) is a way of writing exact text into working memory; see tool-selection-by-freshness.

Source: report · report