The agentic framework ecosystem is rapidly evolving 🚀, with AutoGen, MetaGPT, LlamaIndex, LangGraph, CrewAI and most recently, smolagents. Over the past six months, I've experimented with each of these to varying degrees. While I've seen strong results with publicly hosted models from Anthropic and OpenAI, local Ollama integration 🛠️, particularly for tool-calling …

The AI landscape is shifting again. QWQ-32B from Qwen has just thrown down the gauntlet, demonstrating performance gains that not only surpass distilled DeepSeek R1 32B models but also challenge DeepSeek-R 1-671B on key benchmarks. This isn't just incremental progress; we're witnessing a leap.

My initial experience with QWQ has …

How is AI making you more effective, efficient or creative?

Recent advances in coding models and pair-programming tools like Aider have completely changed how I build tools. What used to take hours—or remain unfinished due to lack of time—is now possible in 30 minutes or less.

In the …

Think multimodal AI needs massive models? Think again!

Microsoft's Phi-4-multimodal is here to challenge that, packing speech, vision and language processing into a lean 5.6B parameters. What's the secret? A "mixture-of-LoRAs" architecture that allows it to handle different data types in parallel, creating a truly unified experience. This means …

How do you currently use LLMs for learning? If you mainly rely on them for quick answers, you're only scratching the surface of their potential.

LLMs can be powerful tools for testing and deepening your understanding of any subject. Instead of just asking for answers, try engaging an LLM in …

Ollama vs. vLLM: A Power-user's Perspective on LLM Serving

For the past 18 months, Ollama has been my go-to tool for running Large Language Models (LLMs). Its reliability and minimalist design, focusing on user experience, are truly commendable. Installation, configuration and model management are incredibly straightforward. However, the rise of …

Ever wondered how well Retrieval-Augmented Generation (RAG) can perform with a classic like Alice's Adventures in Wonderland? I recently used the RAG Assessment (ragas) Python module to automatically create a set of Q&A and then performance benchmark different configurations. Some of the results were surprising.

Dive into my detailed …

Ever felt lost when a sommelier throws out words like "Rhubarb hangs out with cherry cider and the mellowest cinnamon" to describe a wine? ‍ Well - me too!

At the end of last week I was on a quest to bridge the gap between flowery descriptions and actual grape varieties! Inspired …

While text-to-image and text-to-text take most of the Generative AI headlines, the field of text-to-speech (TTS) continues to make steady progress. Recently, I explored the capabilities of Tortoise-TTS, an open-source framework for building high-fidelity TTS systems.

I've captured my research and experimentation in a Jupyter notebook. You can find it …

🔥 Meta's latest release, Llama 3, has delivered an impressive set of Large Language Model (LLM) benchmarks. While the 8B and 70B parameter models show impressive results against closed-source and open-source models such as Claude, Gemini and Mistral, it's interesting to compare improvements of …