AI Forgets My Story Halfway Through: Why, and How to Fix It

AI forgets my story: why ChatGPT and Claude lose track of characters and plot in long fiction, the manual fixes that work, and the tools that automate them.

By · Published October 10, 2026 · Updated October 19, 2026 · 7 min read

Start writing free 1 free credit, no card, no subscription

In chapter three, her brother dies. In chapter seventeen, the AI has him pour the wine at dinner. If you've typed "AI forgets my story" into a search bar after a moment like that, you're far from the only one. It happens with ChatGPT, with Claude and with most other models. The prose can be perfectly fine. The problem is how the model sees your book: in pieces, and only the piece in front of it.

Once you know the mechanics, the fixes are obvious. Some are free and manual. Some tools do them for you.

Why AI forgets my story (and everyone else's)

It only sees what's in the window

A language model has no memory of your book between requests. What it has is a context window: the text sent to it right now. If a fact isn't in that window, it doesn't exist as far as the model is concerned.

Windows are big now. Anthropic's help center lists context windows from 200K up to 1M tokens on paid Claude plans, depending on the model. That sounds like enough for a whole novel, and in raw size it often is. The trouble is everything else in the chat: every draft, every rejected version, every "make it darker", every tangent about the magic system. The book is in there somewhere, mixed in with all the rest.

Long inputs aren't read evenly

Researchers studying long contexts found that models tend to use information at the start and end of a long input better than information in the middle, and that performance drops as the input grows. The paper is "Lost in the Middle" (Liu et al., 2023), and the effect showed up even in models built for long contexts. Your chapter-six detail, buried in the middle of a sprawling chat, is exactly the kind of thing that gets skipped.

Long chats get compressed

When a conversation fills up, something has to give. Claude's help center says that as a chat nears the context limit, Claude summarizes earlier messages to make room. A summary keeps the plot and drops the texture: the scar on her left hand, the fact that he lies about his age, the rule that the magic costs blood.

A new chat starts nearly blank

Open a fresh conversation and the model starts over, apart from whatever memory features you've switched on. ChatGPT's memory can carry details between chats, and both ChatGPT and Claude let you attach files to a Project that every chat inside it can read. Those help. But memory carries over what it happens to pick up, which isn't a reliable copy of your manuscript, and a project file only knows what was true when you last uploaded it. Nobody updates it when chapter fourteen changes something.

There's no structure

This is the real root of it. A chat history is a transcript. Nothing in it marks "this is canon" versus "this was a draft I threw away". The version where the brother lived is sitting in the same history as the version where he died, and the model has no reliable way to tell which one you kept.

The manual fixes that actually work

You can get a long book out of a general chatbot. You just have to do the remembering for it. Here's the kit.

  1. Keep a story bible. One document: every character with name, age, look, what they want and what they know; places; the rules of your world; open threads. When canon changes, update it that day. (Novelcrafter calls this a Codex. Same idea.)
  2. Write a summary after each chapter. A short paragraph: what happened, what changed, who learned what. You can have the AI draft it, but read it and fix it, because a wrong summary is worse than none.
  3. Keep a running recap. A page of "the story so far", rebuilt every few chapters from the chapter summaries.
  4. Send a packet, not a history. Start each session, or each chapter, in a fresh chat. Paste the bible, the recap, the last chapter or two, and the beat you want written. A clean packet usually beats a giant chat.
  5. Mark canon out loud. Tell the model what's decided ("Tomas is dead as of chapter 3, this is final"). Don't leave rejected drafts in the conversation it's working from.
  6. Run a continuity check. Before you accept a scene, ask the model to list anything in it that contradicts the bible. Models tend to be better at checking against a list than at remembering one.

This works. It's also a second job. Every chapter you're the writer and the librarian, and the librarian's work is the first thing to slip when the writing gets good.

For the full chapter-by-chapter routine built on this, see how to write a novel with AI without losing the plot.

Tools that do some of it for you

Fiction-specific tools each have their own answer to this. The big difference between them is who does the bookkeeping.

  • Sudowrite has a Story Bible (characters, worldbuilding, outline, synopsis) that you fill in with AI help, and a Saliency Engine that picks which details the AI sees for each request. Chapter Continuity links chapters so the AI treats them as one story, reading up to 20,000 words back. The character cards are generated from your synopsis or written by hand, and you edit them; the docs don't describe them updating from the manuscript.
  • Novelcrafter has a Codex that recognises names and aliases as you type and tracks how characters change through progressions tied to a point in the story. You write the entries. Scene summaries are written by you or generated when you run the summarize action. You bring your own AI key.
  • NovelAI uses a Memory box and an Author's Note, plus a Lorebook whose entries get inserted into context when their activation keys appear in the recent text. You write and maintain the entries.
  • KudoWrite works in beats. You sketch a beat, the AI writes it, you Rewrite, Expand or Split it, then Commit it into the chapter. On every commit, the AI updates the story bible (characters, places, items, events) and a running summary of the book, so you don't keep them by hand. The bible is yours to read and edit, so when you're stuck you can check what you set up instead of scrolling for it.

Put side by side, the trade-off is simple. The established tools give you more control over what the AI knows, in exchange for more upkeep. KudoWrite automates the upkeep, in exchange for less control. You'll still want to read the bible now and then and correct anything it got wrong, because automated bookkeeping is still bookkeeping.

To be fair about KudoWrite's limits: it's browser-only. The interface is English. (An existing book isn't a blocker: My Books → Import takes .docx, .epub, Scrivener and Novelcrafter projects, plain text and most other formats, and a story bible comes in from Sudowrite CSVs, a Novelcrafter codex, a NovelAI lorebook or AI Dungeon story cards.) It's young, and it has fewer brainstorming tools than Sudowrite and less manual codex control than Novelcrafter.

On cost, KudoWrite has no subscription. You get one free credit on sign-up to try it, then buy one-off packs ($3.50 for 100 credits, roughly a short novel; $7.50 for 500; $12.50 for 1,000), or connect your own OpenRouter or Mistral key and pay the provider directly with no markup. Your work saves to your account automatically and syncs across devices. It also has no content filter of its own, so a dark or explicit scene is your call, within the law, though the models' own behaviour still applies.

If you're weighing the established tools, we've written honest comparisons for anyone looking for a Sudowrite alternative, a NovelAI alternative or a Novelcrafter alternative, including who should stay put.

Which fix fits your book

  • A short story or a few chapters. A good chatbot with a big context window is fine. Keep it in one tidy chat.
  • A novel, and you don't mind admin. The manual kit above, in ChatGPT or Claude, works. The bible and the per-chapter summaries do most of the heavy lifting.
  • A novel, and you want control. A tool where you curate the memory, such as Novelcrafter's Codex or NovelAI's Lorebook.
  • A novel, and you'd rather just write. Something that keeps the bible for you. That's the gap KudoWrite was built for, and you can write a few chapters in KudoWrite and watch the story bible fill in with the free credit.

Whatever you pick, the principle doesn't change. The model will only ever know what's in front of it. Your job, or your tool's, is to make sure the right things are in front of it: what's canon, what's changed, and who's still alive.