Not content with humiliating ChatGPT at the hands of Video Chess on an Atari 2600 emulator, Robert Caruso has tried again, this time with Microsoft's Copilot.
罗伯特·卡鲁索（Robert Caruso）在Atari 2600模拟器上羞辱Chatgpt的视频国际象棋手中不满意，他再次尝试了Microsoft的Copilot。
Theoretically, the result would be the same, and Copilot would take a similar drubbing. Yet... what if Copilot triumphed where ChatGPT could not?"There's no reason to think it would," wrote Caruso, but..."Imagine everyone's head exploding if a MICROSOFT product outperformed ChatGPT."
从理论上讲，结果将是相同的，并且副驾驶会造成类似的丢失。然而...如果副驾驶在Chatgpt无法的地方取得胜利怎么办？卡鲁索写道：“没有理由认为会这样，但是……想象每个人的头是否爆炸了，如果Microsoft产品的表现优于Chatgpt。”
So Caruso fired up the Stella emulator and had a pre-game chat with Copilot to explain what tripped up ChatGPT. He told the chatbot that one of the main reasons why ChatGPT lost was that it could not keep track of the board. If Copilot suffered the same difficulty, then there'd be little point in bothering to play.
因此，Caruso开除了Stella Myulator，并与Copilot进行了赛前聊天，以解释绊倒Chatgpt的原因。他告诉聊天机器人，Chatgpt丢失的主要原因之一是它无法跟踪董事会。如果Copilot遭受了同样的困难，那就不愿意玩了。
With the confidence that only an AI chatbot could muster, Copilot insisted not only could it play chess, but it was also jolly good at it. Caruso said,"It claimed it could think 10–15 moves ahead — but figured it would stick to 3–5 moves against the 2600 because it makes 'suboptimal moves' that it 'could capitalize on... rather than obsess over deep calculations.'"
Copilot相信只有AI Chatbot才能召集，因此，Copilot坚持要下棋，而且也很高兴。Caruso说：“它声称它可以认为10-15的前进 - 但认为它会坚持3-5次对阵2600的动作，因为它使“次优的动作”可以使“它可以利用……”，而不是深入计算。”
Humans strike back at Go-playing AI systems READ MORE
人类反击Go-Go-playing AI系统阅读更多
And keeping track of the board? Copilot boasted,"I make a strong effort to remember previous moves and maintain continuity in gameplay, so our match should be much smoother."
并跟踪董事会？Copilot吹嘘说：“我竭尽全力记住以前的动作并保持游戏玩法的连续性，因此我们的比赛应该更加顺畅。”
Copilot admitted to having the same spatial memory gaps as ChatGPT, yet said it could analyze the current board and pick good moves. Caruso would need to give the chatbot a screenshot of the board after the Atari's move and feed Copilot's moves into Video Chess by hand.
Copilot承认具有与Chatgpt相同的空间记忆差距，但他表示可以分析当前的董事会并选择良好的动作。Atari的移动并用手将Copilot的移动送入视频国际象棋后，Caruso需要给聊天机器人屏幕截图。
The game was afoot!
游戏正在进行！
By now, anybody with experience of today's generative AI systems will know what happened. Copilot's hubris was misplaced. Its moves were... interesting, and it managed to lose two pawns, a knight, and a bishop while the mighty Atari 2600 Video Chess was only down a single pawn. Eventually, Caruso asked Copilot to compare what it thought the board looked like with the last screenshot he'd pasted, and the chatbot admitted they were different.
到现在为止，任何具有当今生成AI系统经验的人都会知道发生了什么。Copilot的傲慢位置放错了位置。它的举动很有趣，它设法失去了两个典当，一个骑士和一个主教，而强大的Atari 2600视频国际象棋只在一个典当下倒下。最终，Caruso要求Copilot将其认为的外观与他粘贴的最后一个屏幕截图进行比较，聊天机器人承认它们与众不同。
"ChatGPT déjà vu."
“ Chatgpt已经看过。”
There was no way Microsoft's chatbot could win with this handicap. Still, it was gracious in defeat:"Atari's earned the win this round. I'll tip my digital king with dignity and honor [to the] the vintage silicon mastermind that bested me fair and square."
Microsoft的聊天机器人无法通过此障碍赢得胜利。尽管如此，这仍然很客气：“阿塔里（Atari）在本轮比赛中赢得了胜利。我将以尊严和荣誉给我的数字国王提供给老式的硅策划者，这使我公平而广场。”
Caruso's experiment is amusing but also highlights the absolute confidence with which an AI can spout nonsense. Copilot (like ChatGPT) had likely been trained on the fundamentals of chess, but could not create strategies. The problem was compounded by the fact that what it understood the positions on the chessboard to be, versus reality, appeared to be markedly different.
Caruso的实验很有趣，但也突出了AI可以胡说八道的绝对信心。Copilot（如Chatgpt）可能已经接受了国际象棋基础知识的培训，但无法制定策略。问题是，它理解棋盘上的位置与现实的事实使问题更加复杂。
The story's moral has to be: Beware of the confidence of chatbots. LLMs are apparently good at some things. A 45-year-old chess game is clearly not one of them. ®
故事的道德必须是：提防聊天机器人的信心。LLM显然在某些事情上很擅长。一场45岁的国际象棋比赛显然不是其中之一。®
