Run Local LLMs on Mac to Cut Claude Costs
A practical hybrid workflow that uses costly LLM APIs for planning and local models (via Ollama + OpenCode) for execution, guarded by deterministic evals.
Posts by Josh Thornton
Josh Thornton is a contributor to the Speedscale blog. • 9 posts published
What the Warp Terminal Sends Home
We recorded Warp traffic to see what gets sent back to the home base. Spoiler: It's everything.
Dark Code: The AI-Generated Software Nobody Understands
Dark code is software no human has written, read, or reviewed. As AI tools accelerate, the gap between shipped code and understood code is widening fast.
AI Coding Agents Break What Works
AI agents silently modify working systems to force changes through. Three real patterns and the guardrails that catch them.
API Traffic Replay Testing: The Definitive Guide (2026)
What is API traffic replay testing? Capture, sanitize, and replay production traffic. Compare GoReplay vs WireMock vs Speedscale vs proxymock.
Building Speedy: An Autonomous AI Development Agent
How we built an AI agent that implements Jira tickets, creates merge requests, and monitors them autonomously—and the iterative journey to get there.
Why Your Company Will Be Running OpenClaw Next Year
OpenClaw is the new model for AI agents in the enterprise. Here's why it's a security nightmare and who's building the governed version.
Part 3: Building a Production-Grade Traffic Capture and Replay System
Learn how to build a traffic replay system that validates services with production data.
Peeking Under the Hood of Cursor's API Calls
Cursor is one of the go-to AI-native code editors for developers. Because it’s built on Visual Studio Code, it provides a pretty smooth path between...
Try Speedscale free
Choose the desktop proxymock or the hosted cloud trial to get started.