
Using GPT-6 Astra, Playco built three themed game prototypes from one grey box foundation and reported 50% fewer manual fixes than with the previous model.
A startup used an AI model to build game prototypes by connecting the model directly to game development engines, allowing the AI to edit scenes, test games, and validate changes within tools developers already use. The AI model produced three different themed game versions from a single foundation prototype, with most working correctly on the first attempt. This approach reduced the need for manual fixes by 50% compared to the previous model, as the AI showed improved ability to reason about space, positioning, and visual elements. The capability to quickly turn multiple game ideas into playable prototypes that developers can test and compare represents the key advance demonstrated.

While restaurant owners might look to generative AI as a shortcut to sprucing up their menu, customers can viscerally sense that something is wrong with the food.
.gif&s=kx7H9a1S3ZIMP7WHNPT2XBlIq6uwDsVvpMZbLf-dnSA)
ChatGPT, Claude, and Grok all suffered outages at nearly the exact same time for reasons that remain murky.

Most teams building a shopping assistant or agent rebuild the same scaffolding: an agent loop, a tool layer over the catalog, an approval gate, and an eval suite. Anthropic has now released that scaffolding as code. This week, they published anthropics/commerce-agents, a reference blueprint containing a shopping agent and a merchant agent, along with four runnable verticals: retail, travel, telecom and entertainment. It ships alongside two write-ups: a product announcement and an engineering de
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven