Hacker News
Generative Agents: Interactive Simulacra of Human Behavior (2023)
The Unreasonable Effectiveness of Grep for LLM-Assisted Coding
Diode – Build, program, and simulate hardware
Anthropic’s Model Context Protocol Is Not an API Standard
zclaw: personal AI assistant in under 888 KB, running on an ESP32
Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents
I Built a Semantic Search Engine from Scratch in Python
I Built a Semantic Search Engine from Scratch in Python
Show HN: VectorVault – A TypeScript-native vector database
Show HN: VectorVault – A TypeScript-native vector database
Diode – Build, program, and simulate hardware
Claude’s Character
Show HN: Firecrawl MCP – Add web scraping to any AI agent
Show HN: Firecrawl MCP – Add web scraping to any AI agent
Show HN: MCPHub – Discover and run MCP servers instantly
Show HN: MCPHub – Discover and run MCP servers instantly
Show HN: Micasa – track your house from the terminal
Learn to Code with Python (for Kids)
Attention Is Off By One
Attention Is Off By One
The Future of AI Software Development
What your Bluetooth devices reveal about you
What your Bluetooth devices reveal
What your Bluetooth devices reveal
X / Twitter
Been exploring what ambient AI could feel like in consumer tools, something you don't have to actively prompt or manage. Ex - Notes that respond to your writing in real time, adding context and connections without breaking flow. https://t.co/GBSmWjlkym
Prototypers: do you still see a role for semi-high-fidelity modalities like Origami? Or just straight from sketchbook/mocks to vibecode?
We present the SOTA feed-forward 3DGS pipeline Selfi, which was accepted by #CVPR2026
Project Page: https://t.co/3T31XcnkpD https://t.co/UD3iH7K0ww
About to feed it all of my screenshots. https://t.co/sREbfjVDYH
@meesrutten https://t.co/jpWtGnxgc2
claude --worktree --tmux: spin up an autonomous Claude on its own worktree, in its own terminal. Fire and forget. Come back to a PR. Or tmux attach to watch it cook (tmux optional if you just want trees).
Huge kudos to Dalton who built this who doesn't have a twitter!
🌲🌳🌴
https://t.co/taVRqwm4dG
We are open-sourcing TTSKit!
Run state-of-the-art text-to-speech models on your Mac and iPhone.
The launch version supports @Alibaba_Qwen Qwen3-TTS and generates audio faster than real-time playback with sub-200 ms time-to-first-byte.
Voice cloning and advanced speed optimizations will be in the next version. Link to the GitHub repo and models on @huggingface in comments.
https://t.co/uNCLciJ6Rd
I made something like Mixbox, but it's optimized for acrylic paint emulation specifically.
It also works with wider color gamuts without requiring dither or terabytes of RAM, and it doesn't require a commercial license from Secret Weapons, which is cool.
https://t.co/rmuLzunWAA https://t.co/0PriJI75Sx
I made something like Mixbox, but it's optimized for acrylic paint emulation specifically. It also works with wider color gamuts without requiring dither or terabytes of RAM, and it doesn't require a commercial license from Secret Weapons, which is cool. https://pastebin.com/Z53LUuNJ