victormustar

How I Use LLMs to Write

Tiny Agents in Python: an MCP-powered agent in ~70 lines of code

An MCP-powered agent in 50 lines of code

The 4 Things the Qwen-3's Chat Template Teaches Us

Hugging Face acquires open source robot startup Pollen Robotics

Gemini Co-Drawing: Doodle on a Canvas with Google Gemini 2.0

Mistral Small 3.1: the best model in its weight class

From Chunks to Blocks: Accelerating Uploads and Downloads on Hugging Face

Janus-Pro: Autoregressive framework unifying multimodal understanding&generation

Wayfarer-12B: An open source AI model that lets you fail and die

Phi-4 weights have been released under MIT license

smolagents: A simple library to build AI agents

How to fine-tune open LLMs in 2025 with Hugging Face

AI Scaling Laws: Behind the Breakthroughs

Show HN: Video Composition Tool Powered by Qwen2.5-Coder and FFmpeg

Large Language Models Can Self-Improve in Long-Context Reasoning

Transformers.js 3.0 Released with WebGPU Support

Janus-1.3B: Unifying Multimodal Understanding and Generation

Llama 3.1 Nemotron 70B: Open model closing the gap with GPT-4o and Sonnet-3.5

Fake Insects: a game where you have to identify AI-generated insects

Idefics3: Open multimodal model based on Llama-3.1-8B

HuggingChat: Chat with Llama 3.1 405B

The Rise of Agentic Data Generation

3D Arena Leaderboard: Evaluate leading generative 3D models

The Farmer Was Replaced: Program and optimize a drone to automate a farm

Phi-3 in-browser inference using WebGPU

Fine-tune Llama 3 with ORPO

In-browser text-to-music generation using musicgen-small