TL;DR — We built a focus-measurement system whose scoring algorithm improves itself. Qwen3.7-Max...
We let Qwen rewrite our scoring algorithm — but only through a clinical-style gate
Related
From "You Have a Bug" to "Here's the Root Cause" - Adding AI Code Analysis to My App Review Pipeline
TL;DR: I built an app review pipeline that classifies bugs and crashes. It was useful but stopped at...
I ran 5 prompt-injection attacks against my chatbot's system prompt. Here's what broke.
Everyone shipping an LLM feature worries about jailbreaks, but 'is our system prompt actually resilient?' gets answered by vibes. So I built a tester for it.
MCP Session Architecture: Scale Agent Integrations Without Sticky Servers
A practical guide for AI product builders designing scalable MCP servers with stateless sessions, resumable streams, load balancers, Redis-backed state, and safer agent tool execut...