The notebook — memory across chats.
Open a new chat and the screen is wiped clean. So how does an assistant ever “remember” you at all?
The last two pages showed everything in a conversation sharing one window. Here is the part that surprises people: the moment you close a chat and open a new one, that window is wiped completely clean. The new chat starts blank. The model has no idea what you said yesterday — or even a minute ago, in the chat you just closed.
So by default, an assistant does not remember you between chats. Every new conversation is a fresh screen. The review monitor is wiped at the end of every match — whatever was on it is gone. To recall a striker's habit next season, the VAR writes it in a notebook they carry between matches.
That notebook is the trick. Some assistants keep a small store of chosen facts saved outside the chat window — a name, a preference, a detail or two. It survives the wipe. At the start of a new chat, a few of those facts are quietly loaded back into the fresh window, so they are present from the very first message.
The key idea is that these are two different things. The window is temporary working memory, wiped every chat. The notebook is deliberate, lasting memory — a short list of saved facts. Only the second one carries over.
Three facts are already in this chat. Choose memory off or on, start a new chat, and see what survives the wipe.
Memory is just a list, loaded back in.
Remembering is not the model holding on to your old chats. It is a short list of facts, kept on the side and re-loaded into each new window at the start.
# a new chat starts with an empty window — it remembers nothing on its own system = briefing # memory is a SEPARATE store that lives outside any single chat memory = load_saved_facts(user) # e.g. ["Marcus", "left wing", "Rovers fan"] # at the start of a new chat, saved facts merge into the ONE system message if memory: system += "\n\nAbout this user: " + "; ".join(memory) window = [ {"role": "system", "content": system} ] # only now does the new chat "know" you — the facts were re-loaded, not remembered reply = var.chat(window + [{"role": "user", "content": message}])
Two kinds of memory.
The chat window is working memory — wiped clean the moment a conversation ends. An assistant only recognises you across chats if it keeps a separate notebook of saved facts and loads them back into each new window. No notebook, no recognition.
So “remembering” is not the model clinging to your past chats. It is a small, deliberate list of facts, saved outside the window and re-loaded at the start — something you can usually see, edit, and delete.