MicroZig to Adopt Strict No LLM / No AI Policy
MicroZig plans to adopt a strict ban on LLM and AI use. Its code of conduct covers the Zig Embedded Group’s GitHub organization and Discord server. (github.com)
October 2026 marks a new inflection point for AI-assisted game development, Simon Willison argues: Claude Opus 5.5 can now produce games that are not merely playable but genuinely enjoyable, with stronger 3D modeling, music generation, and - most importantly - game design. The key shift is that models can create satisfying gameplay loops with little direction, making the harder task finding original, delightful ideas. Willison says GPT-6 Astra can build games but has not yet matched Opus 5.5’s feel for fun. His experiments were browser-based HTML and JavaScript games, often made without examining the code.
Four projects illustrate the change. Tree Appreciator, made from one prompt, is a relaxing 3D spot-the-difference game with collectible trees. Emberwick grew through repeated prompts and playtesting into a roughly 15-minute fantasy RPG, with a village, underground passages, quests, magic, and a story whose ending moved its creator; fixing gameplay bugs required more work than producing the world and narrative. Battle Drones, a real-time strategy game, improved dramatically after Opus 5.5 was asked to make it “a LOT more fun” and convert it to 3D. It now includes multiplayer, maps, replays, rule variants, and matches between AI models. Together, these projects suggest that making a compelling game is newly accessible, while meaningful human contribution increasingly lies in choosing concepts and refining what the model generates.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
MicroZig plans to adopt a strict ban on LLM and AI use. Its code of conduct covers the Zig Embedded Group’s GitHub organization and Discord server. (github.com)
Qwenputer embeds a deterministic RISC-V CPU in Qwen3.5 4B’s weights, using its Gated DeltaNet state as RAM to run arithmetic and code without external tools. The experiment also adds in-model file storage and is available with its code on Hugging Face and GitHub. (divagr.com)
The New York Times is adding more AI features to its Cooking app. Users have reacted negatively to the changes. (niemanlab.org)
Google’s AI-powered search gave some U.S. users no clear answer about who won the 2020 election, though Gemini answered correctly and Google appeared to fix the issue. The incident renews concerns about the company’s AI quality control, especially after similar failures in 2024. (karlbode.com)
Marissa Mayer drew criticism for saying her AI app helped describe her daughter in generic terms for a school presentation. The backlash reflects concerns that tech leaders are too detached from everyday life to understand how the public wants to use AI. (techcrunch.com)
Google AI Mode sometimes avoids directly saying Joe Biden won the 2020 US presidential election, instead directing users to official sources. Its responses vary across users and election years, while answers become more direct when asked outside the US. (arstechnica.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.