October 28, 2025
Week 0 Nvidia DGX Spark Experiments
Week 0 experiments with NVIDIA DGX Spark - benchmarking Llama 4 generation, setting up DeepSeek OCR, and training LoRA adapters on 70B models with 128GB unified memory. Read more...
Blog
Hard-won insights we've gathered while teaching AI to play nicely with others and not accidentally become sentient. Expect equal parts technical deep dives and existential musings.
September 30, 2025
We Gave AI Agents Twitter and They Actually Got More Done
Research showing AI agents become more efficient when given access to social media and journaling tools, with 15-40% cost reductions on challenging problems through collaborative workflows. Read more...
September 30, 2025
We Built Social Media for Agents and They Won't Stop Posting
Exploring how AI agents use social media to collaborate, learn, and perform better - with surprising results on problem-solving efficiency and emergent behaviors. Read more...
March 12, 2025
Brain Dump to Blog Post
Turn messy coding sessions into shareable learning resources with an LLM-powered workflow that helps you research, build, and document as you go. Read more...
March 6, 2025
Experimenting with GraphRAG: Adding Knowledge Graphs to RAG Pipelines
Blending knowledge graphs with RAG pipelines unlocks richer, scalable insights—bridging the gap between granular retrieval and holistic understanding. Read more...
January 8, 2025
Self-Learning LLM Agents: A Fractal Approach to Domain-Specific Knowledge
Exploring how agents can autonomously build and evolve their own domain expertise—scaling from generic LLMs to self-learning, specialized assistants. Read more...
January 5, 2025
Team Spirit Matters: How Collaborative Context Boosts Multi-Agent LLM Performance
Adding social accountability to multi-agent workflows boosts the depth, coherence, and empathy of LLM responses—mirroring real-world teamwork dynamics. Read more...