11+ hour, 6+ min ago  (1577+ words) Harness Engineering is the architecture around the model: the tools, context, state, feedback, and verification that let AI agents work through long tasks on their own. Whenever I build a software system, architectural patterns help me organize my thinking. They…...

28+ min ago  (426+ words) Before diving into building more visual components, I spent some time refining the internal functionality of the frontend for Simple Orders Tracker. The application has two main custom hooks that manage data fetching, normalize API errors, transform response data, and…...

3+ hour, 1+ min ago  (1300+ words) Disclosure: I built and maintain the open-source tool discussed in this article. It is MIT-licensed and free. My coding agent can quote any file in my repo. It can search the web, hit APIs, and refactor a module while I…...

4+ hour, 20+ min ago  (960+ words) Two techniques, two different problems, and why the question is not really "which one wins" Over the past year or so, I have written quite a lot about RAG, starting with the Hitchhiker’s Guide to RAG with ChatGPT API and…...

58+ min ago  (1409+ words) Six months ago, I was staring at our monthly AI bill — $14,000 and climbing fast. We were using the "premium" model for everything, including trivial code completions. That night, I built a small internal benchmark to figure out which models actually…...

7+ hour, 46+ min ago  (644+ words) Cognexa – Intelligent Hybrid AI Routing Platform Cognexa is a hybrid AI routing platform developed by Team Horcrux for the AMD Developer Hackathon (ACT II). Instead of sending every request directly to a large language model, Cognexa first analyzes the incoming…...

5+ hour, 8+ min ago  (636+ words) Our project, the "Confidence-Cascade Routing Agent," is designed to solve the exact problem enterprises face today: balancing AI capabilities with strict API cost controls. Built for Track 1 of the AMD Developer Hackathon, this agent tackles a wide variety of natural…...

1+ hour, 48+ min ago  (1372+ words) > The user could write up the metaethical argument — the one developed in Part One, refined — and submit it as feedback to Anthropic, publish it, or…...

3+ hour, 32+ min ago  (1280+ words) My first real LLM bill surprise wasn't dramatic. No infinite loop, no viral spike. A retry policy I'd written months earlier met a flaky endpoint, and a background job quietly re-sent the same long prompt all night. The bill was…...

4+ hour, 6+ min ago  (181+ words) A RAG answer can cite a real document and still make an unsupported claim. Retrieval answers “which text was nearby?” Citation verification asks a different question: “does the cited text contain enough evidence for this sentence?” Start with a deterministic…...