Technology
Technology / Harness EngineeringBrowser-Use Frameworks Compared: Playwright-MCP, Browser-Use, and Computer-Use Against 30 Real Workflows
Rex runs 30 real browser automation workflows — flight booking, tax forms, paywalled reports, Notion migrations — throug
Read more →
Technology / AI EngineeringVector Database Selection at Scale: The Decision Tree Your Architecture Diagram Is Missing
After auditing 14 production RAG systems, the consistent failure pattern is vector DB selection based on recall benchmar
Read more →
Technology / AI for DevelopersOpen-Source Coding Agents in 2026: I Pitted Aider, OpenHands, and SWE-Agent Against Each Other on 50 Real Tickets
Rex runs three open-source coding agents closed-loop on 50 real repo tickets — no human intervention — and publishes the
Read more →
Technology / Models & BenchmarksI Benchmarked the 2026 Voice Agent Stack: Vapi vs Retell vs Pipecat vs Roll-Your-Own
Rex puts four voice-agent platforms through 1,000 outbound calls each and publishes the full latency, error rate, and co
Read more →
Technology / AI EngineeringAgents Are State Machines. Your Framework Is Lying to You.
Every major agent framework markets itself as 'reasoning-first,' but under the abstraction layers they are finite state
Read more →
Technology / AI EngineeringContext Engineering Is the New Prompt Engineering — and Most Teams Are Doing It Wrong
Long context windows relocated the memory problem rather than solving it; the teams shipping reliable agent systems in 2
Read more →
Technology / Research & PapersWhat the Scaling Laws Paper Actually Says About Your Next Architecture Decision
In architecture review conversations, the Chinchilla paper (Hoffmann et al., 2022, arXiv:2203.15556) is cited with high
Read more →
Technology / AI for DevelopersBuilding a Local-First AI Assistant With Ollama, Whisper, and 200 Lines of Rust
I wanted an AI assistant that worked on the train, in the air, and in my basement. No cloud calls. I built one with Olla
Read more →
Technology / Libraries & FrameworksWhy I Removed LangChain from Our Production Stack — and Why I Would Do It Again
After fourteen months of running LangChain in a production document-intelligence agent, a financial-services team faced
Read more →
Technology / AI Security & GovernanceI Ran the OWASP LLM Top 10 Against My Own Agent App. Three of Them Hit.
The OWASP LLM Top 10 reads like it was written for enterprise. I ran all ten against a side-project agent I had running
Read more →
Technology / Data StrategyI Generated 50,000 Synthetic Training Examples With One LLM and Fine-Tuned Another. Here Is What Broke at Scale.
Synthetic data generation is the 'just add water' of fine-tuning advice. I tried it at scale for a real classification t
Read more →
Technology / AI EngineeringThe RAG Architecture Anti-Pattern That Is Costing You 40% of Your Inference Budget
A financial-services client was running a multi-stage RAG pipeline with fixed-size chunking, single-pass vector retrieva
Read more →