Noah Brier
Model Madness: A Tournament of Tool Calling
Tested 45 AI models in a March Madness bracket challenge with easy, medium, and hard tool sets to reveal how scaffolding impacts AI performance.
We like to write. We believe writing is a powerful tool for thought and it's much harder to fake your way through paragraphs than it is through a conversation.
Noah Brier
Tested 45 AI models in a March Madness bracket challenge with easy, medium, and hard tool sets to reveal how scaffolding impacts AI performance.
Noah Brier
Gemini Flash delivers around 80% of frontier LLM intelligence at just 10–25% of the cost, making it the defining model in the $1 intelligence tier.
Aaron Rutledge
Claude Code feels like a finely tuned video game—complete with tight feedback loops, progressive mastery, recoverable failures, and clear agency—turning...
James Gross
On Bloomberg’s Odd Lots, Noah Brier highlights Claude Code as a “computer within your computer,” using file system access and Unix commands to bypass...
Noah Brier
AI empowers multi-hyphenate professionals to amplify diverse skills, exposing the absurdity of forced early specialization.
Noah Brier
I built Aesthete—a local-only Typescript/NextJS/Tailwind site powered by Claude Code and Anthropic frontend design skills—to curate nearly 200 aesthetically...