Guessing Games
Bigger Than a Breadbox: A 20 Questions Game
Ten well-known things sealed before you start, each with fixed answers to the questions people ask most: ask yes or no, and name each one in as few questions as you can, twenty at most.
- Players
- 1+
- Length
- 30–60 min
- Rated
- All ages
- Version
- 1.0.0
- Updated
Works with ChatGPT · Claude. Free, no signup.
Opens ChatGPT or Claude with the play prompt ready; press send if it hasn't started. Same link on your phone as on your desktop. Another app? Copy the play prompt into it. This game needs a chat that can open links: its answers stay in a sealed file on this site. What works where.
Want it as an installed app, or the card itself?
The game card is every rule of the game, about 13k characters, but not its answers: those stay in a sealed file on this site, so even pasted, Bigger Than a Breadbox: A 20 Questions Game needs a chat that can open a link. Pasting the answers in yourself would spoil it. The Skill installs Bigger Than a Breadbox: A 20 Questions Game into Claude on any plan: download it, then turn on code execution under Settings → Capabilities and add it at Customize → Skills → + → Upload a skill.
Bigger Than a Breadbox: A 20 Questions Game is a 20 questions game where the AI's answer is locked before you ask: ten sealed things, fixed answers to common questions, every spent question logged. One or more players, 30–60 min a run, free to play inside ChatGPT or Claude. No signup and nothing to install: open it in your assistant, or paste the play prompt into any chat that can open links.
How to start
- Open it in your AI. Tap Open in ChatGPT or Open in Claude and press send, or paste the play prompt into any assistant that can open links. The chat must be able to open a link, because the AI, as the Answerer, reads a sealed file.
- The first thing opens. The Answerer fetches the sealed file, reads you the start of the SHA-256 fingerprint, and opens the first thing with its class: animal, vegetable or mineral.
- Ask, then name it. Ask yes/no questions and name the thing with "Is it a …?". Fewer questions score more; twenty is the limit.
- Check the answers. After the tenth thing, open the sealed file, copy all of it, and paste it at aigamecards.com/verify; then check every logged answer against it.
Questions
- Can ChatGPT play 20 questions?
- Not reliably on its own. In a plain chat the thing you are guessing is not fixed anywhere you can check, so the AI can answer each question by what sounds likely and settle on a thing only when you guess. A 2026 paper, LLMs Can't Play Hangman (arXiv 2601.06973), proves that an agent restricted to the public conversation cannot both keep a secret unresolved and stay consistent with it. This card fixes the ten things first: each one and its answers to sixty-seven common questions are sealed under SHA-256 before your first question. The card tells the AI to fetch that file at the start, rule other questions by a written procedure and log every answer that costs a question, so you can check them against the sealed file afterwards.
- What does the seal prove, and what doesn't it?
- It proves that the ten things and their coded answers were fixed before you asked anything; you can rebuild the hash at aigamecards.com/verify. It does not prove that every answer was right. Questions the codes do not cover are ruled by a written procedure from each thing's sealed description, and the AI can misapply a rule, so every answer is logged with the code or words it used, and the sealed file is yours to read afterwards.
- Is this 20 questions game good for kids and car trips?
- Yes. Every thing is one a child and a grandparent both know, nothing is gory, and nothing asks for a name or a personal detail. One person types and everyone asks, so it works as a car game or at the table. Ten things take an estimated forty-five minutes, about four or five minutes each, and a save code lets you stop for a break and carry on later. With younger children a parent should be at the keyboard.
- What if my question isn't a plain yes or no?
- The AI can also answer SOMETIMES (true of some ordinary ones, like a hat's colour) or PARTLY (true of a part, like a hammer's wooden handle); both cost a question. Questions that are not yes or no, name two or more things, add more to a name, or ask about the name come back REPHRASE, and trivia no card covers, such as who invented it or a date, comes back NOT ON ANY CARD; both are free. Examples after a description are ignored: "Is it a pet, like a cat or a dog?" is ruled as "Is it a pet?". The sixty-seven coded questions were chosen from the questions players asked in the Allen Institute for AI's twentyquestions dataset (48,638 in-game questions from crowd-sourced games). Other questions are ruled by the written procedure, and every answer that costs a question is logged.
- Does the chat have to be able to open a link?
- Yes. The card tells the AI to fetch the sealed file from aigamecards.com at the start and, if it cannot, to say so and stop; pasting the file yourself would show you all ten answers. A chat that ignores the card can still make things up, and the log and the sealed file let you catch that afterwards. ChatGPT opens it; aigamecards.com/launch-matrix shows which other apps do.