A novice set out to test whether AI could help someone with no coding, 3D modeling, or game-development experience build a substantial game. The goal was a browser-playable opening to a science-fiction RPG-shooter, with combat, dialogue, a simple story, cutscenes, and free movement through a location. Using a one-page concept brief, ChatGPT to shape the initial instructions, and Codex to generate and revise the game, the creator had a playable prototype within hours and a working end-to-end version after a few days. The project used mostly free tools; Codex was the only paid service, costing about $15 in usage.
The creator generated character images, turned them into 3D models with Hunyuan3D, converted the files, and used Mixamo’s free animations. A consistent visual guide, inspired by Star Wars’ Battle of Hoth, helped establish the look. The process still demanded substantial human judgment: animation setup was fiddly, some creatures had to be redesigned to move on two legs, AI-generated sound lacked atmosphere, and dialogue needed rewriting. Several days went into fixing glitches and adding fog, snow, music, and cutscenes. After about ten days, the result was a playable but imperfect demo. The experience suggests AI makes experimentation and prototyping accessible to beginners, while emphasizing that a designer’s taste and choices remain central to crafting mood, story, and feel.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Amazon updated its software engineer guidelines to emphasize results over specific tools, including AI. It says engineers must combine AI with human judgment and expertise while adapting to rapid changes in software development. (aboutamazon.com)
Trump said he would ban the term “artificial intelligence” in official documents and other materials. He wants it replaced with “super intelligence,” which he calls a more accurate name. (reuters.com)
Researchers found that pushing individual neurons in Qwen3-8B led it to identify as 34,220 different personas, rather than as an AI. The results come from one prompt, and the persona labels were assigned by an AI judge without human review. (qwen-neurons-site.vercel.app)
New records show Medicare’s WISeR AI prior-authorization program has caused care delays, denials, operational problems, and reported patient harm. The EFF says the findings highlight the need for stronger legal limits on government use of automated decisions. (eff.org)
An Anthropic hiring manager has dropped coding interviews because AI can outperform candidates on those tests. Junior engineers can still excel by using AI, questioning assumptions, and bringing fresh perspectives; hunger can outweigh tenure. (felixrieseberg.com)
Anthropic expanded its GSA agreement, offering government agencies a 40% discount on Claude products and implementation support, with no minimum spending requirement. The deal extends to state, local, tribal, and territorial governments and is estimated to save the government $1 billion. (anthropic.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.