The story I told across the last twenty-one posts ended with twenty-two tools running at my...
#22 Tool #23 Is the Blog You're Reading Right Now
Related
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.
I stopped replaying my entire codebase to Codex and Claude Code
I kept hitting the same problem in long Codex and Claude Code sessions: the agent was capable, but...
From ChatGPT to AI Agents: What Actually Changed Between 2022 and 2026
I recently gave this talk in English to my classmates at an English school in Baguio, the...