Adam Lucek

Build AI Agents That Work While You Sleep | Deep Agents

LLM Agents tackle longer and more complex task with deep agent frameworks! Resources: Notebook and Agent Code - https://github.com/ALucek/deep-agents-walkthrough LangChain …

Making Computer & Browser Use Agents

How do you embody the digital soul? Resources: Blog Post - https://lucek.ai/blogs/compuse ScreenEnv - https://huggingface.co/blog/screenenv Browser Use - https://github.com/browser-use/browser-use Language …

Do Reranking Models Actually Improve RAG?

To try everything Brilliant has to offer—free—for a full 30 days, visit https://brilliant.org/AdamLucek/ You’ll also get 20% off an annual …

400x Faster Embeddings! - Static & Distilled Embedding Models

To try everything Brilliant has to offer—free—for a full 30 days, visit https://brilliant.org/AdamLucek/ You’ll also get 20% off an annual …

Real-Time UI Generation: Building Dynamic Web Experiences with GenUI

The next generation of websites may not look quite the same to anyone ever with generative UI/UX techniques Chapters: 00:00 …

Fine Tuning Video Generation Models | Make Your Own AI Videos

Training video models with… Images? Turns out video diffusion and image diffusion is similar enough that we can train the …

Large Multimodal Models Are The Future - Text/Vision/Audio in LLMs

Vision and auditory capabilities in language models bring AI one step closer to human cognitive capabilities in a digital world …

Why Every AI Developer Should Learn Model Context Protocol (MCP)

Connecting datasources to LLM applications has never been easier! Resources: Code: https://github.com/ALucek/quick-mcp-example Anthropic MCP Blog: https://www.anthropic.com/news/model-context-protocol MCP Docs: https://modelcontextprotocol.io/introduction MCP …

I Made 3 AI Tools That Solve Real Problems

The practical and useful applications of artificial intelligence from a day-to-day practitioner. Convert PowerPoint presentations into semantically rich text using …

I Trained an LLM to Think Deeper (Here's How)

Turns out reinforcement learning is all you need Check out my prior video on RL: https://youtu.be/qTY4Rr-x5q0?si=pgTpw9r9xwkuZJM6 Resources: Code: https://github.com/ALucek/GRPO-Training/tree/main Model: …

Improving RAG Retrieval by 60% with Fine-Tuned Embeddings

Actually worked better than I thought lol Resources: Code: https://github.com/ALucek/ft-modernbert-domain Model: https://huggingface.co/AdamLucek/ModernBERT-embed-base-legal-MRL Dataset: https://huggingface.co/datasets/AdamLucek/legal-rag-positives-synthetic Philipp Schmid’s Blog: https://www.philschmid.de/fine-tune-embedding-model-for-rag#3-define-loss-function-with-matryoshka-representation Matryoshka Representation …

Building Intelligent AI Agents with Open Source LLMs | smolagents

What’s next... large agents? Resources: Code: https://github.com/ALucek/smolagents-guide Smolagents docs: https://huggingface.co/docs/smolagents/index Smolagents blog: https://huggingface.co/blog/smolagents DynaSaur - Large Language Agents Beyond Predefined …

Find the BEST RAG Strategy with Domain Specific Evals

Creating custom RAG chunking and embedding strategies with domain specific evaluation experiments Resources: Notebook Repo: https://github.com/ALucek/custom-rag-evals/tree/main Prior Chunking Breakdown: https://youtu.be/Pk2BeaGbcTE?si=pWK6hkXPnJCyb4Ux …