I kept hitting the same problem in long Codex and Claude Code sessions: the agent was capable, but...
I stopped replaying my entire codebase to Codex and Claude Code
Related
Built an AI Document Assistant That Runs Code in a Sandbox
Every AI document tool falls into one of two categories: Chatbots that can talk about your files but...
Where does Secure by Design End? A 3D/4D Model
I’ve been thinking about a surprisingly intricate question: Where does Secure by Design...
Could GPT-5.6 Sol Have a Dangerous Vulnerability?
A hypothesis about RLHF, logic-first alignment, and the possibility that technically correct AI responses may still harm emotionally vulnerable users.