Hacker News Reader

shreyaskon Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

thank you!

shreyaskon Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

https://huggingface.co/spaces/shreyask/needle-playground

shreyaskon Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

https://huggingface.co/spaces/shreyask/needle-playground

shreyaskon Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model

Built a browser version of this runs entirely client-side via onnxruntime-web, no server: https://huggingface.co/spaces/shreyask/needle-playground

shreyaskon Add voice support for terminal coding assistants on Apple Silicon

Bidirectional voice MCP server for terminal coding assistants — listen (STT) and speak (TTS) on Apple Silicon via mlx-audio.

shreyaskon LLM and MCP in Browser

Run next-gen hybrid models in your browser with tools powered by the Model Context Protocol (MCP) enabling secure, real-time connections to remote servers.

shreyaskon Shipping a Neural Network on iOS with CoreML, PyTorch, and React Native

Really good end-to-end article! Enjoyed reading it.

shreyaskon All the steps needed to create deep dream animations on EC2

These steps are cool and very detailed, also check out https://github.com/VISIONAI/clouddream which is containerized so you can try it on local machine as well as on EC2.