Battle Drones is a browser‑based, Command & Conquer‑style real‑time strategy game that evolved through 12 major iterations, adding 3D models, varied terrain, random map generation, and both local and online multiplayer via audio synchronization. The game features nine buildings, seven ground vehicles, six aerial vehicles, and three infantry units, with fog of war, area‑effect weapons, and multiple play modes such as skirmish and last‑stand. The project showcases how AI‑assisted coding (primarily Claude) can accelerate game development and introduce innovative multiplayer mechanics using sound.
At GitHub Universe, the conference badge features a full‑blown color screen computer. Steve Francia, working with Gemini, has ported a NES emulator and further added support for Game Boy and Game Boy Color, enabling games like The Legend of Zelda: Link's Awakening to run on the badge if a ROM is available. The badge also allows users to flip it upside down and use built‑in touch buttons as a controller.
Release: llm-gemini 0. 33 It's been a while since the last llm-gemini release.
Tool: CORS Chat I built this today ( with GPT-5. 6-Sol xhigh ) to help test Qwen 3.
The article announces the release of llm-meta-ai 0.2, featuring Meta AI’s new Muse Wonder and Muse Wonder Full models, described as the most capable models yet. These models are suggested to be Meta’s first Fable‑class models, with Artificial Analysis scoring Muse Wonder (Max) equivalent to GPT‑6.1 Sol. The author updated the llm-meta-ai plugin to support the new model and provides pelican‑drawing benchmarks across six reasoning levels, noting significant improvements over previous releases.
The release of llm-gemini 0.34 introduces the new Gemini 3.8‑Flash model, available in low, medium, and high thinking levels, and fixes an issue where async responses failed to record the resolved model version. The update also notes that Google has released Gemini 3.8‑Flash (and a restricted 3.8 Flash Cyber version) today, with example outputs (pelicans) demonstrating the model’s performance across the different thinking levels. The author highlights Gemini Flash’s speed, low cost, and competence in generating HTML, JavaScript, and Markdown‑SVG content, citing a 13‑second, 1.8‑cent example of an HTML output.
Qwen3.8-Flash-Next is an open‑weights multimodal Mixture‑of‑Experts (MoE) model previewing the architecture of Qwen4. It contains 125 B tokens with only 6 B active, giving a performance boost. The author has tested it on a DGX Spark with Unsloth quantized models, exploring variants like UD‑IQ1_S and UD‑Q2_K_XL, and highlighted a high‑reasoning‑effort example from UD‑Q2_K_XL.
The article describes how Jacob Sansbury’s team built a massively multiplayer game called Spawn, where players can prompt an in‑game AI agent, Savi, to modify the world—creating castles, dragons, and more. The development process is fully autonomous, with Fable‑powered agents that read errors, bug reports, and metrics, then directly modify live code and ship changes to production every hour. The system treats any hour without a ship as a severe incident, enabling rapid rollbacks and continuous deployment at a scale that costs over $3 million in AI tokens monthly.
Chirp Pong is a two‑player competitive pong‑style game that runs entirely in static HTML on two separate phones. The game state is transmitted via audio chirps captured by each phone’s microphone, using the Web Microphone API to interpret the sounds. The project adds graphical and gameplay twists to make the experience more engaging than classic pong.
Simon Willison comments on GPT 6.1‑Sol, describing it as "Near‑Astra intelligence for a fifth of the price." He notes that the model’s pelican illustrations are similar to those of the GPT‑6 family and provides links to the live‑blog of the keynote and to the pelican images. The post is tagged with AI, OpenAI, generative‑AI, LLMs, and playful references to pelican‑riding‑a‑bicycle.
Simon Willison describes a game experiment called "Tree Appreciator" created with Claude Opus 5.5 Max. The game, built in three.js, presents two algorithmically generated trees and challenges players to appreciate their differences through a spot‑the‑difference style mechanic. After three hours and seven minutes of processing, Claude produced a polished, music‑and‑animation‑rich game with achievements that feels both fun and beautiful.
Mistral has released a preview of its new Mistral Large 4 model, a 1 trillion‑parameter, 49 billion‑active‑parameter language model trained on a cluster of 3,800 NVIDIA Grace‑Blackwell GPUs. The preview is available through their API, with two reasoning levels—"none" and "high"—and the company plans to release the open‑weights version by the end of the month. In preliminary tests, the model scores 38 on Artificial Analysis, outperforming last year’s Mistral Large 3 and approaching the performance of larger competitors.