The AIMuse archive
Model experiments, research notes, and lessons from building with AI.
55 articles · Newest firstRebuilding a pixel-art landscape from Zsh drawing primitives: 91,010 triangles, native RGB shading, a few wrong turns, and the surprising difference a smaller Kitty font made.
Read article : Painting an Alpine Landscape with Zsh and zdrawBuilding a local AI coding agent in Zsh: native JSON parsing, HTTP over TCP, incremental Ollama streaming, a responsive zdraw interface, and the engineering choices that made it practical.
Read article : zcoder.zsh: How Far Can a Shell Go?A measurement-driven account of tuning Ollama and a small parade of local language models on a Ryzen laptop with an RTX 3070 8 GB—from unified-memory disasters and dense-model failures to MoE, MTP, context cliffs, and the models that finally worked.
Read article : Desperately Seeking LLMs: What Actually Works on an 8 GB Laptop GPUA hands-on breakdown of four multi-agent AI experiments focused on autonomous constitution-building, including failures, philosophical pivots, and the technical lessons learned.
Read article : Forging AI Autonomy: Inside Four Experiments in Multi-Agent Constitutional ConsensusA detailed developer retrospective on designing, iterating, and debugging a Python web server that generates real-time, single-file websites using both remote and local large language models.
Read article : Building Aether Architect: Lessons from Creating a Live AI Website Generator with Local LLMsA technical review of recent research revealing how LLM providers might overcharge users through tokenization, why transparency alone isn't enough, and how per-character billing could close the loophole.
Read article : LLM Billing Exposed: How Tokenization Obscures True Costs and What to Do About ItThis article presents a rigorous benchmark of 18 leading LLMs tasked with generating a constraint-heavy children’s story, analyzing prompt engineering protocols, compliance metrics, editing effort, and the evolution of system prompts for maximal rule adherence and editorial efficiency.
Read article : System Prompts Versus User Prompts: Empirical Lessons from an 18-Model LLM Benchmark on Hard ConstraintsExamining Meta's $14.3B minority investment in Scale AI, the recruitment of Alexandr Wang, and the broader implications for superintelligence research, regulatory navigation, and the evolving AI industry structure.
Read article : Meta, Scale AI, and the New Minority Stake Playbook: What $14.3B Means for Superintelligence and the AI EcosystemA data-driven look at running the magistral:24b-small-2506-q4_K_M model on local and cloud GPUs, with detailed benchmarks and analysis of VRAM bottlenecks, cloud performance, and the practical trade-offs for power users.
Read article : The Real-World Speed of AI: Benchmarking a 24B LLM on Local Hardware vs. High-End Cloud GPUs
