Published Date : 09/06/2025
In a surprising and somewhat humorous turn of events, ChatGPT, the advanced AI model from OpenAI, has been defeated by the Atari 2600 in a beginner-level chess match. Robert Jr. Caruso, a Citrix Architecture and Delivery specialist, discovered this anomaly and shared his findings on LinkedIn. Caruso pitted the 1979 Atari Chess title, played within an emulator for the 1977 Atari 2600 console, against the sophisticated ChatGPT 4o.
The concept of computing performance being measured by chess-playing ability is deeply rooted in tech history. Chess computer games have been popular since the early days of consoles and home computing. Enthusiasts have long tried to grade the abilities of various chess engines against those of professional grandmasters. Notably, IBM’s Deep Blue supercomputer made history in 1997 by defeating Garry Kasparov, the reigning world chess champion at the time. Deep Blue’s brute force approach, evaluating 200 million possible chess moves per second, was instrumental in its victory. However, Kasparov won the overall series 4-2 after losing the first match.
In 2025, the Deep Blue supercomputer’s processing power of approximately 11.4 GFLOPS seems minuscule compared to even entry-level modern processors. Given this context, one would expect an Atari Chess running on a nearly 48-year-old console to be easily beaten by ChatGPT. However, Caruso’s experiment proved otherwise.
The Atari 2600, powered by a MOS Technology 6507 processor running at 1.19 MHz, had very limited computing power, measured in KFLOPS rather than GFLOPS. The chess engine in Atari Chess only thinks one to two moves ahead, according to Caruso. Despite this, he attempted to make things easier for ChatGPT by changing the Atari chess piece icons, which the chatbot initially blamed for its losses. However, even with these adjustments, ChatGPT made enough blunders to be laughed out of a third-grade chess club, as Caruso humorously noted.
Tragically, despite ChatGPT 4o’s promises to improve its game, the old 8-bit gaming platform continued to outperform it. Caruso provided direct assistance during the game sessions, but ChatGPT could not muster the intelligence to beat the Atari Chess 'beginner' opponent and eventually conceded, according to Caruso’s LinkedIn post.
This story highlights the unpredictable nature of AI. While AI can sometimes astonish with its capabilities, it can also be laughably inadequate. This particular instance with ChatGPT and the Atari 2600 falls firmly into the latter category.
Q: What is ChatGPT?
A: ChatGPT is an advanced AI language model developed by OpenAI. It is designed to engage in natural language conversations and perform a wide range of tasks, from answering questions to generating text.
Q: What is the Atari 2600?
A: The Atari 2600 is a home video game console released in 1977. It was one of the first successful consoles and played a significant role in the early history of video games.
Q: Why did ChatGPT struggle against the Atari 2600 in chess?
A: Despite the Atari 2600's limited computing power, ChatGPT made several blunders during the game. The exact reasons are not clear, but it could be due to the AI's limitations in understanding the game or the specific challenges posed by the Atari Chess engine.
Q: What is the significance of using chess to measure computing performance?
A: Chess is a complex game that requires strategic thinking and has been used as a benchmark for computing performance. The ability of a computer to play chess well is often seen as a measure of its intelligence and processing power.
Q: What is the history of IBM's Deep Blue in chess?
A: IBM's Deep Blue was a supercomputer that made history in 1997 by defeating world chess champion Garry Kasparov. Deep Blue used brute force techniques to evaluate millions of possible moves per second, showcasing the potential of advanced computing in complex tasks.