Sam Witteveen
VERIFIED TECHNICAL DOSSIERSources checked

Sam Witteveen

Co-Founder of Red Dragon AI

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Sam Witteveen. Every entry undergoes editorial source verification.

#1
IMPLEMENTATION Checked Sep 22, 2026

LangChain and LLM Agent Notebook Implementations

Authored dozens of open-source Jupyter notebooks with thousands of stars demonstrating tool integration, multi-agent debate, and local RAG retrieval pipelines.

Model & Execution Context:LangChain, ChromaDB, Hugging Face Transformers, Ollama.
Scope & Limitations

Notebook workflows require refactoring into stateless services for production high-concurrency environments.

#2
EXPLANATION Checked Sep 22, 2026

LoRA and QLoRA Fine-Tuning of Open Weights Language Models

Produced rigorous tutorials examining adapter weights rank selection, NF4 quantization, gradient checkpointing, and evaluation across Llama and Mistral model families.

Model & Execution Context:Hugging Face PEFT, TRL, bitsandbytes 4-bit quantization, Llama-3.
Scope & Limitations

LoRA adapters require careful learning rate warmup to prevent catastrophic forgetting of base pre-training knowledge.