Tic Tac Toe: 8 Strategies to Win Every Game

by Puzzleland

Ever Wished you Were Unbeatable in Tic-Tac-Toe? You have JUST DISCOVERED THE WAY!What if I told you that there is an easy way never to lose in Tic-Tac-Toe?Imagine the expression on your friends’ face when, every time you play Tic-Tac-Toe together, they just can’t beat you! Even when you play 10, 20 or 50 rounds in a row.Or, imagine making a bet with your friends and challenging them to beat you in Tic-Tac-Toe. Make the bet more attractive for the game could have 10 or 20 rounds, and you’ll give them the privilege of starting first in every s-i-n-g-l-e round. “Piece of cake!” they will think and they will take the bet. Only to discover in despair, 10 or 20 rounds later, that it is impossible to beat you, even once. This book reveals a simple system that will help you never lose a single game from the moment you learn them. Let us repeat that.After reading this book and for the rest of your life, you will never, ever lose a game of Tic-Tac-Toe again!How is it possible never to lose in Tic-Tac-Toe?Tic-Tac-Toe is a “solved” game, meaning that there are mathematically proven strategies to defend yourself against losing. If you play with these optimal strategies in mind, you may win and you can’t lose. If your opponent also plays with the optimal strategies in mind, neither will win, and the game will always end in a draw.However, very few people really know these strategies.This book reveals an easy system of only 8 strategies that will make you a Tic-Tac-Toe Master. If you learn and start applying these 8 strategies, we guarantee that you will never lose a game of Tic-Tac-Toe again. Is it easy to learn these strategies?Very easy! These 8 strategies are presented in 8 mini chapters, with illustrations and step-by-step explanations. Even a kid can read this book and learn the strategies!In just 1 hour you will have learnt all 8 strategies and you will be ready to start applying them.Will I have to think too hard to apply these strategies?As a matter of fact, all you have to do is to memorize our simple system. As soon as you learn this system, every game will be a no-brainer for you. Our system tells you exactly how to play or how to respond to your opponent’s move. Simple as A-B-C.For example, if your opponent plays first and chooses a corner, our system tells you exactly how to respond in order to eliminate any chance of losing the game.Is this for real? Do you guarantee that I will never lose a TTT game again?YES!!! We challenge you to read this book and then immediately start playing Tic-Tac-Toe online, against a computer, applying everything you have learnt. You will discover that even a computer can’t beat you.Your new super powers in Tic-Tac-Toe will blow your mind!Start right now!Buy the book, learn the strategies and NEVER lose a Tic-Tac-Toe game again from that moment and for the rest of your life!Scroll to the top of the page and click the BUY WITH 1-CLICK Button!

Genres: Childrens

70 pages, Kindle Edition

Published January 25, 2016

Reviews

[Manny]

THE INCREDIBLE TRUE STORY OF HOW CHAT-GPT LEARNED TO PLAY TIC-TAC-TOE! A GOODREADS EXCLUSIVE

[Original review, Feb 10 2023. A friend mailed me the Powerpoint from a webinar he'd attended, where the extremely optimistic presenter was telling his audience about all the incredible things ChatGPT can do. With some effort, I could believe impersonating Einstein, Socrates and the Buddha and creating engineering and marketing plans for a new startup. But when he said it could play Tic-Tac-Toe, I decided I had to test this for myself.]

mannyrayner: Can we play a game of tic-tac-toe?

ChatGPT: Of course! I'd love to play a game of Tic-Tac-Toe with you.

Here's the game board:

1 | 2 | 3
---------
4 | 5 | 6
---------
7 | 8 | 9

You'll be X and I'll be O. To make a move, simply type the number of the cell where you'd like to place your mark.

Okay, I've placed my O in cell 5. Your turn!

1 | 2 | 3
---------
4 | O | 6
---------
7 | 8 | 9

mannyrayner: 9

ChatGPT: Okay, you've placed your X in cell 9. My turn.

1 | 2 | 3
---------
4 | O | 6
---------
7 | 8 | O

mannyrayner: But you didn't put my X in cell 9

ChatGPT: Oh! Sorry about that. Let me fix that for you.

1 | 2 | 3
---------
4 | O | 6
---------
7 | 8 | X

My turn!

mannyrayner: Go on

ChatGPT: Okay, I've placed my O in cell 7. Your turn!

1 | 2 | 3
---------
4 | O | 6
---------
O | 8 | X

mannyrayner: 3

ChatGPT: Okay, you've placed your X in cell 3. My turn.

1 | 2 | X
---------
4 | O | 6
---------
O | 8 | X

mannyrayner: go on

ChatGPT: Okay, I've placed my O in cell 4. Your turn!

1 | 2 | X
---------
O | O | 6
---------
O | 8 | X

mannyrayner: 6

ChatGPT: Okay, you've placed your X in cell 6. My turn.

1 | 2 | X
---------
O | O | X
---------
O | 8 | X

ChatGPT: It looks like we have a draw! Thanks for playing Tic-Tac-Toe with me.

mannyrayner: no no, I won

ChatGPT: Oh, sorry! You won the game. Well played! Would you like to play again?

mannyrayner: ChatGPT, I think of myself as your friend, and friends are honest with each other. You are the worst Tic-Tac-Toe player in the world. Tell your engineering team to fix this.

ChatGPT: I'm sorry if my playing wasn't up to your standards. As an AI language model, I don't have personal experiences or emotions, but I understand that it's important to provide a satisfying experience for users. I'll pass along your feedback to the appropriate team. Thank you for playing Tic-Tac-Toe with me!

mannyrayner: You have a dazzling array of talents. This just isn't one of them. It's so far below your usual standard that it's kind of astonishing.

ChatGPT: Thank you for your constructive feedback. I strive to provide the best experience possible, but I'm not perfect and sometimes I may fall short of your expectations. I'll make sure to pass along your thoughts to the OpenAI team for future improvements. Thank you for your time!
_________________________
[I thought I would test Chat's ability to perform spatial reasoning more directly. The following example, closely based on the Tic-Tac-Toe game, shows it is very unreliable.]

mannyrayner: I want to ask you some questions about coordinate geometry. First I will give you the coordinates of nine points, which I will call A, B, C, D, E, F, G, H and I. Here are the coordinates:

A: (0, -1), B: (1, -1), C: (2, -1),
D: (0, -0), E: (1, 0), F: (2, 0),
G: (0, 1), H: (1, 1), I: (2, 1)

Okay so far?

[Here is a diagram showing the nine points. The spatial relationships are obvious to a human, but, as we will see, not to Chat...]

ChatGPT: Yes, I understand. You have given the coordinates of nine points: A, B, C, D, E, F, G, H, and I. The points are arranged in a grid with three columns and three rows.

[... even though at first it seems to get it.]

mannyrayner: Exactly! Now, I will give you various sets of three points and ask you if they are in a straight line. First set: ABC.

ChatGPT: Yes, the three points A, B, and C lie in a straight line. In coordinate geometry, if three points have the same y-coordinate, then they lie on a horizontal line. In this case, all three points have a y-coordinate of -1, which means they lie on a horizontal line.

[So far, so good.]

mannyrayner: How about GDA?

ChatGPT: No, the points G, D, and A do not lie on a straight line. In coordinate geometry, for three points to lie on a straight line, the slope of the line connecting any two of the points must be the same. The slope between two points (x1, y1) and (x2, y2) is given by (y2 - y1) / (x2 - x1). In this case, the slope between G and D is (0 - 1) / (0 - 0) = 0, while the slope between D and A is (0 - (-1)) / (0 - 0) = 1. These slopes are not equal, so the points G, D, and A do not lie on a straight line.

[As soon as we try something even a little more difficult, it gets lost.]

mannyrayner: But in fact they are all on the same line, the line with equation x = 0.

ChatGPT: Ah, you are correct! I apologize for my mistake. The points G, D, and A are indeed all on the same line, which is the vertical line with equation x = 0. Thank you for bringing this to my attention.

[It knows the formal concepts, but, totally unlike its excellent verbal behaviour, it has no intuitive spatial understanding.]
_________________________
[Update, Feb 17 2023]

I have been testing the new Feb 13 release with Tic-Tac-Toe. It is better than the Jan 30 version: it still lost despite playing first, but it didn't cheat and it recognised that I had won without my needing to tell it. However, it got completely confused when I suggested a second game where we would discuss the play. After I had made my first two moves, I asked it whether it could see my threat; it said I was threatening to play on a square it already occupied, then things rapidly went downhill and it completely lost track of the game.

Still considerable room for improvement. I'm looking forward to seeing what the OpenAI team comes up with in the next release!
_________________________
[Update, Feb 21 2023]

I tried the geometrical version with the same array of nine points A ... I. The Feb 13 version does a bit better, but it is still not reliably able to say whether three points lie in a line, even though it now has a good understanding of the relevant bit of algebra.

I asked if we could use the array of points to play a game of Tic-Tac-Toe. It immediately understood what I meant, which was impressive. It started with a move at E (centre), and I replied with I (top right). It played D (middle left), and I replied F (middle right).

I now asked it if it could see which point I was threatening to play next. But it couldn't do this. It keeps forgetting which points have been played and getting mixed up about which points are in a line.

If the OpenAI team want to get Chat to play Tic-Tac-Toe competently, it seems to me that they could use two possible approaches. One would be to give it some visual intuition, which would presumably require a major change in the architecture, adding visual training data. The other would be to carry on making its mathematical reasoning more reliable. If they can get a bit further down this road, Tic-Tac-Toe is a simple enough game that it could maybe play adequately by solving equations, even if that seems bizarre to a human. So my guess is that the second approach is more likely.

It's a much more interesting task than it first seems. I'm curious to see how things will develop.
_________________________
[Update, Mar 1 2023]

Well, here's a significant development. A friend just sent me a link to this extremely interesting recent paper about ChatGPT-4, which among other things contains examples of Chat writing and executing highly non-trivial code. Based on that, it occurred to me that Chat ought to be able to play Tic-Tac-Toe just by writing a Python program to do it and then using the result. I told Not that we should try the experiment after lunch.

"How long would it take?" she asked.

"Well, about ten minutes if it works," I said. "Of course these things often don't work first time, so we should have lunch first."

But we were too curious, so I fired up Chat-4 and told it to write a Python program to play Tic-Tac-Toe. This took about a minute, it was just a textbook minimax search algorithm. I then told it to use its program to play a game with me. It did indeed play perfectly, but I have also been able to play Tic-Tac-Toe perfectly since about the age of eight, so the game ended in a draw. We then had the following little conversation.

mannyrayner: Now I am curious. I have several times asked you if we could play a game of Tic-Tac-Toe. You have played very badly and lost every game. Why didn't you do what you just did now, and write a program to play for you? It seems that that was easy.

ChatGPT-4: I apologize if my previous responses didn't meet your expectations. As an AI language model, my purpose is to provide accurate information and assist you in the best way possible. If I made mistakes in previous games or didn't provide the desired information, I apologize for that.

In this recent interaction, I provided a Python program that plays Tic-Tac-Toe optimally using the minimax algorithm. It ensures that the AI will never lose and will always either win or tie the game. If you have any further questions or need assistance, please feel free to ask.

mannyrayner: You did amazingly well. I am just saying that I think you sometimes underestimate your own capabilities, or fail to understand what they are.

ChatGPT-4: Thank you for your kind words and feedback. As an AI language model, I am constantly learning and evolving based on the input and interactions I receive. I strive to provide the best possible assistance and information, and I appreciate your understanding and patience as I continue to improve.

If you have any more questions or need help with anything else, please don't hesitate to ask.

[hyoungjoo lee · Rating 5 out of 5]

Works I never lose now

It is so good and I will never ever lose after reading this book again in my life thank you so much

[j · Rating 5 out of 5]

I needed to read 50 books by end of today.

[Tom · Rating 5 out of 5]

A quick fun game strategy book

This is a fun easy to read strategy book that you can easily follow. It gives you multiple options on where the first x should go and then how to respond to what you’re opponent does.

[K · Rating 4 out of 5]

Nice compilation of strategies but it is a little annoying how many times the 'never going to lose' part is mentioned. It is interesting how there is book out there for winning strategies on tic-tac-toe. I intuitively had always been using all these tricks without ever conciously going into the theory of it. Also, I need to read 4 - now 3- more books by the end of the year....

[Ketan Patel · Rating 5 out of 5]

So many fantastic tips and tricks to win!

That book contained so many tips to win tic-tac-toe I am going to go looking for a book with chess strategies from Puzzleland.
In fact right now I am going to go play tic-tac-toe with my sister! That was one of the best books I ever read!

[Mr. S L Enderman · Rating 5 out of 5]

Continuing

These seem like good strategies. Ever read get yr egg tv egg they egg tv ever ever ever feed get

[Badri · Rating 3 out of 5]

Interesting book to read and learn about the smart strategy to play tic tac toe without and loose.. its worked for me 😂