4 posts tagged with "ai"

AI agents are getting more capable, but they are also getting increasingly expensive in a way that is easy to overlook.

A single agent run may repeatedly pay for a system prompt, conversation history, retrieved context, memory, tool schemas, tool outputs, intermediate reasoning, and the final response. When the workflow becomes multi-step, token consumption compounds quickly.

Most benchmarks ask a binary question: did the agent complete the task?

I wanted to ask a second one:

How many tokens did it actually need to succeed?

That question led me to build Suffice, an open-source toolkit for measuring the minimum token budget an AI agent needs to complete a task while preserving a required level of quality.

Suppose you had to score an entire film or television series tomorrow.

Not one cue. Not one trailer track. An actual musical world: opening theme, character motifs, tension beds, battle cues, intimate scenes, transitions, reprises, and a final sequence that still sounds as if it belongs to the same score.

Could you create all of that with a system such as Suno using only prompts?

The surprising answer is: partially — and perhaps much more convincingly than people expect.

The important part is understanding why.

A few months ago I found myself in a familiar situation: I needed to document a side project quickly. I had used Docusaurus before, loved it in theory, but every time I bootstrapped a new doc site I ended up fighting Node.js toolchains, React component boilerplate, and config files before I had written a single line of actual documentation. MkDocs was simpler, but it felt dated and lacked the AI-native features I increasingly wanted in my workflow.

So I did what every engineer does when the existing tools annoy them enough — I built my own. The result is ncmds (No Code Markdown Documentation Sites), and this post walks through the thinking, the architecture, and the lessons learned.

After months of deep dives into AI music systems, research papers, and hands-on experimentation, I decided to consolidate everything I learned into a comprehensive open-source educational resource: Neural Audio Theory.

This project explains how modern AI music systems are actually built — from the fundamentals of digital audio processing all the way to transformer architectures and diffusion model training.