FocusLM Research
Research-grounded notes on AI memory, context windows, and retrieval. These are the findings FocusLM is built on — the evidence for structured, long-term memory over an ever-bigger prompt, and for an AI that actually knows your world.
Encrypting AI memory: why a key per project beats a key per database
An AI that remembers your life holds material you would not hand to a stranger. We encrypt every memory file and chat message under a key belonging to that project alone — and the research explains why the obvious alternatives leak.
ReadMore context isn't always better: what happens past 64k tokens
A large study across 20+ models found that stuffing more retrieved text into the prompt often stops helping — and for many models starts hurting — well before the window is full. Bigger is not the same as better.
ReadWhat if an LLM managed memory like an operating system?
The context window is small and fixed. MemGPT borrows a 40-year-old idea from operating systems — a memory hierarchy with paging — to let a model work with far more information than fits in the window.
ReadRAG vs long context: which one should you actually use?
When a model can read a million tokens, is retrieval obsolete? A Google DeepMind study says no — long context wins on quality when you can afford it, retrieval wins on cost, and a simple router gets most of both.
ReadLost in the middle: why long context windows quietly fail
LLMs use the start and end of a long context far better than the middle — a U-shaped effect that persists even in models built for long context. Here's what the research shows and what it means.
Read