Watching the Black Box
The final part of a series on agent harnesses. We started with the model-plus-harness idea, then built subagents, gave them a safe place to work, and wired up tools, memory, and workflows. This last p
Jun 6, 20267 min read17
Command Palette
Search for a command to run...
#optimization
Articles tagged with #optimization
One Agent Is Not Always Enough
Part two of a series on agent harnesses. If you have not read part one, it introduces the idea that an agent is a model plus the harness around it. This piece builds on that, so a quick skim first wil
Jun 5, 20267 min read22
Agent = Model + Harness
If you have ever called an LLM API, you already know the basic shape of it. You send some text, you get some text back, and the connection closes. That is a model. It is good at producing language, bu
Jun 5, 20268 min read87
Using Web Workers in JavaScript - An Old School Way of Writing Code
Introduction JavaScript is a single-threaded language, meaning it can only perform one operation at a time. This limitation can lead to performance issues, especially when dealing with complex computations or heavy tasks that can block the main threa...
Jul 18, 202411 min read100
Intricacies of Fail-Open Mechanism
In the digital age, where data breaches and cyber-attacks are increasingly common, the importance of robust authentication mechanisms cannot be overstated. These systems not only serve as the gateway guarding access to sensitive information and funct...
Feb 25, 20247 min read70