Feed aggregator

A browser based air traffic control simulation where agentic AI acts as a control tower with an objective of landing airplanes.

It was developed as an experiment in exploring agentic AI capabilities for controlling multiple objects in an active space.

The results were spectacular as a single agent can not only land multiple airplanes, but it also prevents collisions with other airplanes in small busy spaces.

Comments URL: https://news.ycombinator.com/item?id=47206784

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=MkfHD2ShE5s

Comments URL: https://news.ycombinator.com/item?id=47206776

Points: 1

# Comments: 0

Article URL: https://github.com/susam/hnskins

Comments URL: https://news.ycombinator.com/item?id=47206775

Points: 2

# Comments: 0

Article URL: https://janhoon.com/blog/building-with-an-ai-that-remembers/

Comments URL: https://news.ycombinator.com/item?id=47206766

Points: 1

# Comments: 1

Samsung's new top-of-the-line phone packs upgrades to the camera and battery, but here's what I've loved using so far.

One of the biggest tech events of the year may not be on your radar, and not because it's happening in Barcelona.

Can the Blues derail their capital rival's title charge?

We've been building dev tools and noticed more and more users tell us they found us because "ChatGPT recommended it" or "Claude suggested it". Not Google, but AI.

There's no Google Search Console for this. No way to know if e.g. GPT-5.2 is recommending your library, where it ranks you, or whether Gemini even knows you exist. We couldn't find a tool that solved this, so we built one.

GeoStorm monitors multiple AI models on a schedule. You define search terms (e.g., "best Python async framework"), and it queries ChatGPT, Claude, Gemini, etc. via OpenRouter. It then parses the responses, tracks your brand mentions, calculates recommendation share, and alerts you when things change - a new competitor appears, your ranking drops, a model stops mentioning you.

Technically: it's a single Docker container. FastAPI backend, Astro/React frontend, SQLite, APScheduler running in-process. No Redis, no workers, no external dependencies. One OpenRouter API key gives you access to all models.

> docker run -d -p 8080:8080 -v geostorm-data:/app/data --name geostorm ghcr.io/geostorm-ai/geostorm

That gives you a working instance with 90 days of demo data so you can explore everything immediately. Add your OpenRouter key to start monitoring your own project.

MIT licensed. Would love feedback on the approach - especially from anyone who's already thinking about AI-driven discovery for their tools.

GitHub: https://github.com/geostorm-ai/geostorm Webiste: https://geostorm.ai/

Comments URL: https://news.ycombinator.com/item?id=47206476

Points: 1

# Comments: 0

I built this because existing monitoring solutions (Prometheus+Grafana, Portainer) felt like overkill for simply watching a few Docker containers.

DockWatch is a single container that provides: - Real-time dashboard (CPU, memory, network, disk, temperature) - 6 anomaly detection rules with Telegram alerts - Self-signed HTTPS or Cloudflare Tunnel for remote access - Single HTML file dashboard — no build step

Stack: FastAPI, aiodocker, Chart.js, SQLite. 4 Python dependencies total. ~50MB memory.

Design philosophy: do one thing well. Monitor containers, detect anomalies, send alerts. No container management, no custom metrics, no query language.

Install: git clone https://github.com/deep-on/dockwatch.git && bash install.sh

I'd love feedback on the architecture and what features would make this more useful. The anomaly detection rules in particular — are the default thresholds reasonable?

Comments URL: https://news.ycombinator.com/item?id=47206470

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=K0dgrPRWPCs

Comments URL: https://news.ycombinator.com/item?id=47206469

Points: 1

# Comments: 0

Article URL: https://knowablemagazine.org/content/article/living-world/2026/why-heterothermic-animals-control-their-body-temp

Comments URL: https://news.ycombinator.com/item?id=47206453

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=l6ZcFa8pybE

Comments URL: https://news.ycombinator.com/item?id=47206444

Points: 1

# Comments: 0

Article URL: https://ics.uci.edu/2026/02/25/uc-irvine-researchers-expose-critical-security-vulnerability-in-autonomous-drones/

Comments URL: https://news.ycombinator.com/item?id=47206442

Points: 1

# Comments: 0

Article URL: https://felixbarbalet.com/simple-made-inevitable-the-economics-of-language-choice-in-the-llm-era/

Comments URL: https://news.ycombinator.com/item?id=47206424

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=X764gI8fPwc

Comments URL: https://news.ycombinator.com/item?id=47206422

Points: 1

# Comments: 0

Article URL: https://contextgeneric.dev/blog/v0.7.0-release/

Comments URL: https://news.ycombinator.com/item?id=47206419

Points: 1

# Comments: 0

Article URL: https://forum.support.xerox.com/community?id=community_question&sys_id=c9b4b1a197dbba501b263f21f053af32

Comments URL: https://news.ycombinator.com/item?id=47206414

Points: 2

# Comments: 0

I started building Frame as a terminal-first, lightweight IDE and open sourced it. Now I'm pushing it toward becoming a full platform for developing and managing larger projects. What I've been able to build in about a month with Claude Code is honestly insane. Here's where Frame is today: Core - Terminal-first platform with up to 9 terminals in a 3x3 grid - Multi-AI support — Claude Code, Codex CLI, and Gemini CLI in one window - Automatic context injection via wrapper scripts for non-native tools Project Management - Standardized project structure (AGENTS.md, STRUCTURE.json, PROJECT_NOTES.md, tasks.json) - Context, architecture, and structure management that persists across sessions - Built-in task tracking with AI integration Integrations - GitHub extension — issues, PRs, branches, and labels right in the sidebar - Plugin system with marketplace support Under the hood - 115+ IPC channels powering real-time bidirectional communication - 36+ modules across main and renderer processes - Pre-commit hooks for auto-updating project structure - Prompt injection system for universal AI tool compatibility - Transport layer abstraction — preparing for Electron IPC → WebSocket migration

Comments URL: https://news.ycombinator.com/item?id=47206398

Points: 1

# Comments: 0

Hi HN, I’m a student and I’ve spent the last few months building Autolang—an embedded language and VM from scratch in C++.

I built it because I needed a specialized runtime for high-frequency, short-lived tasks (like AI agent loops) where Python/Lua startup latency and GC overhead become actual bottlenecks.

Core Architecture:

Arena-restart: No Tracing GC. It prioritizes allocation speed (~2x faster than Lua). Memory is wiped instantly between tasks via a restart() mechanism.

Fast Compilation: 100k classes compile in ~888ms (Single-pass).

Lightweight: The VM is designed for a ~2ms startup target.

The Trade-off: Execution is currently 2x-5x slower than Lua as I'm still optimizing the bytecode dispatch (if-chains).

I’d love to hear your thoughts on using Arena-restart for autonomous scripts and any advice on optimizing dispatch without bloating the startup time.

Comments URL: https://news.ycombinator.com/item?id=47206397

Points: 1

# Comments: 0

process demo - https://i.redd.it/fbhlwsq1gcmg1.gif render demo - https://i.redd.it/smddwtryhcmg1.gif

I love making creative software. I spent a few years making pixel art software but recently have gotten into 3d animation and 2d animation and really wanted a way to realize crazy ideas.

Blockbench didn't feel quite right, spline is super well made but felt catered too much to just idle website animations, and I really didn't want to fall down a master class in Blender just to make some silly stuff. While I'm definitely not discounting Blender's literal powerhouse functionality, I wanted something smaller, easier to adopt, and something directly inside the web ecosystem. So that when I want to make assets for silly games I won't have to jump through any hoops to make everything match up and render nicely. So, I made Topomaker (tentative name).

It's sporting your basic 3d modeling, coloring, and animation. It's currently supporting exports to mp4's and gifs for sharing, and then glb's and obj's for making games in threejs.

I literally just started it a couple weeks ago so there are probably tons of bugs, so maybe not for anything serious, but feel free to play around with it and let me know what you think!

Comments URL: https://news.ycombinator.com/item?id=47206387

Points: 3

# Comments: 0