The Spectrum faithfully recreates the 80s original with its rubber keys and classic games, delighting older gamers, while younger players may face a steep learning curve due to tricky controls and tough gameplay. However, modern features like save and rewind help mitigate that frustration. It was made with as few components as possible and connected easily to the TV. Programs ran from compact cassettes, some of you may remember listening to music from these before the advent of CDs. It was possible to program in Basic and play some games. The ZX Spectrum's competitor was the Commodore 64, a popular machine that Retro Games had already recreated.

Another month, another revolutionary generative AI development that will apparently fundamentally alter how an entire industry operates. This time tech giant Microsoft has created a "gameplay ideation" tool, Muse, which it calls the world's first Wham, or World and Human Action Model. Microsoft claims that Muse will speed up the lengthy and expensive process of game development by allowing designers to play around with AI-generated gameplay videos to see what works. Muse is trained on gameplay data from UK studio Ninja Theory's game Bleeding Edge. It has absorbed tens of thousands of hours of people's real gameplay, both footage and controller inputs.

In the future, Microsoft suggests, you may be playing AI. No, not on the battlefield, but on games that actually use AI to simulate the entire game itself. As a first step, Microsoft has developed an AI model, called WHAM, that "beta tests" games early in the development cycle using AI instead of human players. Gamers know that realistic AI can turn a good game into something great, like how the older F.E.A.R. games would realistically model how soldiers might react to a hostile, armed player. Microsoft's World and Human Action Model (WHAM) takes the opposite approach -- it tries to figure out how human players will react in a given situation, right down to a specific frame or setup within the existing game world.

The rapid advancement of large language models (LLMs) has accelerated their application in reasoning, with strategic reasoning drawing increasing attention. To evaluate the strategic reasoning capabilities of LLMs, game theory, with its concise structure, has become the preferred approach for many researchers. However, current research typically focuses on a limited selection of games, resulting in low coverage of game types. Additionally, classic game scenarios carry risks of data leakage, and the benchmarks used often lack extensibility, rendering them inadequate for evaluating state-of-the-art models. Specifically, we incorporate all 144 game types summarized by the Robinson-Goforth topology of 2 2 games, which are constructed as classic games in our benchmark. Furthermore, we employ synthetic data generation techniques to create diverse, higher-quality game scenarios through topic guidance and human inspection for each classic game, which we refer to as story-based games. Lastly, to provide a sustainable evaluation framework adaptable to increasingly powerful LLMs, we treat the aforementioned games as atomic units and organize them into more complex forms through sequential, parallel, and nested structures. We conducted a comprehensive evaluation of mainstream LLMs, covering tests on rational reasoning, reasoning robustness, Theory-of-Mind capabilities, and reasoning in complex game forms. The results revealed that LLMs still have flaws in the accuracy and consistency of strategic reasoning processes, and their levels of mastery over Theory-of-Mind also vary. These achievements are largely attributed to LLMs' ability to assimilate vast amounts of knowledge during training, emerging with the capacity to organize information at a coarse level and link knowledge at a finegrained level through their internal representations (Min et al., 2023; Zhao et al., 2023). These core capabilities have driven the success of LLMs in numerous reasoning tasks, including mathematical reasoning (Hendrycks et al., 2021; Zhang et al., 2023), commonsense reasoning (Sap et al., 2019; Bisk et al., 2020), logical reasoning (Lei et al., 2023), and strategic reasoning (Lorè & Heydari, Work done during an internship at the University of Hong Kong. The dataset and evaluation codes will be available at https://github.com/PinkEx/TMGBench. Among these, strategic reasoning has attracted considerable attention due to its multi-agent nature and close association with social intelligence (Gandhi et al., 2023). Strategic reasoning refers to the cognitive process of anticipating, planning, and responding to others' actions to achieve specific objectives within competitive or cooperative contexts (Zhang et al., 2024a).

GuideGeek uses artificial intelligence to help plan vacations. In your beach bag, sunscreen, a towel, sunglasses and plenty of snacks are essentials. While some people can easily spend the whole day lying in the sun with a good book in hand, others enjoy more of an activity-filled day. This is where beach games come into play. There are so many different games that your family, friends or significant other can enjoy during your day in the sand.

Despite the sunny spring skies in San Francisco this week, the mood among nearly 30,000 video game industry professionals was gloomy as they descended upon the city for the yearly Game Developers Conference (GDC). Some were so frustrated with the state of affairs in their business that they organized a group screaming session in a park. "Those of us who have a job and can afford to be here are going through the motions and trying to have a good time," said Maxi Molina, a game developer attending the event from Spain. "But the vibe is rancid in the industry right now." The gaming industry saw more than 10,000 workers laid off in 2023, up from 8,500 in 2022, according to the Game Industry Layoffs project, which tracks game developer and publisher job losses globally.

The Nintendo eShop for the Wii U and 3DS game consoles officially closed for business on March 27th, 2023, permanently disabling all new purchases on the platforms. We knew this was coming. Nintendo quietly announced the eShop's closure over a year ago, asserting that it was the "natural life cycle for any product line as it becomes less used by consumers over time." That doesn't make it any less of a loss for Nintendo fans, because legally playing some of these console's best games is now not only harder, but in some cases, nearly impossible. The time to argue that Nintendo should keep this aging digital storefront open has long since passed (though yes, they should have).

Game-playing artificial intelligence (AI) systems have advanced to a new frontier. Stratego, the classic board game that's more complex than chess and Go, and craftier than poker, has now been mastered. Published in Science, we present DeepNash, an AI agent that learned the game from scratch to a human expert level by playing against itself. DeepNash uses a novel approach, based on game theory and model-free deep reinforcement learning. Its play style converges to a Nash equilibrium, which means its play is very hard for an opponent to exploit.

DeepNash uses a novel approach, based on game theory and model-free deep reinforcement learning.

It's the early 1990s, and you – a college dropout – have been tasked with babysitting your chronically disappointed father's launderette business. It is not an exciting job. You pick up rubbish, you unclog the toilet, you load laundry into machines and take it out again. But in the back room, there's a small collection of arcade machines to help customers while away the time as their shirts dry, and there's enough money in their coin hoppers to buy a whole new cabinet. And so you begin the slow process of secretly transforming your father's business into a thriving arcade, reinvesting the cash you make from washing people's dirty underwear into buying more video games.