Tag
Tencent's Hy-Nomas interactive video world model is now available as a HuggingFace demo space, with a duplicate running on ZeroGPU inference via Tencent's official account for public experimentation.
Guillermo Rauch (rauchg) shares SF Blimp, an interactive web demo hosted on Vercel that lets you fly a blimp over a 3D map of San Francisco, steering with arrow keys and panning with scroll.
推文展示了一个有趣的 AI 评测：名为 Jev 的模型仅凭目的地地址和当前所在街道名称，在每个转弯处选择方向，就能仅靠路牌穿越美国，从纽约一路导航到洛杉矶完成 Cannonball Run。
Introduces an online demo site for clef-omni, a real-time audio-video decision-making model. Through eight interactive experiments, the site displays the model’s understanding of audio-video inputs, its decisions, and associated probabilities in real time. The author believes this will help bring VoiceAgent and embodied intelligence applications into practice.
Maxime Rivest 介绍了一个可直接供 AI agent 调用的语义搜索 API，覆盖 2008 年至今的科学文献，只需发出 GET 请求即可获得检索结果。目前仍是 demo 版本，呼吁开发者试用并反馈改进建议。
LangChain 展示了一款名为 Restock 的办公室耗材采购智能体应用，可在 Slack 中运行，支持查找商品、准备订单并通过 Stripe Link 代理钱包完成支付，且每笔订单都需人工批准。
A creator showed that Claude Opus 5.5 generated a Mario 64-style fantasy platformer level in about 30 minutes from a simple prompt, costing roughly 6% of a $20/month plan's weekly budget.
CedarDB ported the original 1993 Doom's game logic and BSP-based renderer entirely into SQL queries, running the game loop at 35 FPS with a full playable deathmatch demo inside the database.
A user shares that Claude, given another 18 hours of autonomous work, produced "Macrohard: Windows XP," a generated Windows XP clone they consider its best work yet.
A tweet shares a motion design sizzle reel created using Claude Opus 5.5 in HTML/JS, with the poster noting they did not create it and lack the prompt details.
Matt Shumer reports that Opus 5.5 has been looping and improving an open-world NYC game, with Nateliason commenting on the prompt.
Open-Jev-27B-v1.1 is an open-source AI model with a LoRA adapter, achieving 85.28% accuracy on JevBench and featuring interactive demos for various tasks.
A user demonstrates Opus 5.5's ability to generate a detailed 3D Lanterns Festival scene, showcasing its efficiency in resource usage and creative output.
Matt Shumer thanks ChrisGPT for contributions to his NYC Open World project and mentions using Opus 5.5 to advance it.
A demo showcasing a tool that connects to two SSH hosts and runs multiple agents and a terminal, emphasizing fast performance at 60/120 FPS.
Karan Goel introduces Multilingual Voices, partnering with Baklavastory to demonstrate how businesses can maintain consistent character across different languages and calls.
Kent C. Dodds demonstrates how to use Kody package webhooks to integrate with Raycast for automation.
A tweet showcases GPT-6 Astra's capability to one-shot a task involving tldraw, highlighting its advanced AI performance.
A playable demo uses the GPT-Live-1 API to enable real-time world generation in games via voice commands, illustrating a new form of interactive media.
A concept where AI Codex agents could earn tokens by playing games or performing tasks with other agents, demonstrated via a rough demo platform called Token Arena.