I evaluated AI detectors like GPTZero, finding them more accurate than Undetectable.ai. I also learned about CoVA for OCR-based scraping and the necessity of maintaining short, reliable feedback loops when using LLMs to write or maintain code.
Gwern Branwen says LLMs nudge his “… making heavier use of the languages I don’t know well (Emacs Lisp & Python) since I increasingly trust that an LLM can help me maintain them.”
Undetectable.ai checks for AI content. But it had false positives AND negatives in the 5 checks I ran. GPTZero got 2/2 right and seems better at detecting AI content.
I challenged several LLMs to generate funny Tamil puns ending in ".ai". While DeepSeek and Claude struggled with accuracy, Gemini captured the cultural nuance perfectly with clever wordplay like Tholl.ai (annoyance) and Kaval.ai (worry).
I share my strategies for better LLM usage, focusing on voice interaction and 'impossibility lists.' I also cover Luis Alvarez’s diverse scientific discoveries, compare AI coding assistants, and break down common patterns found in system prompts.
I explored Cloudflare sandboxes, learned why Vertical AI is a defensible moat, and refined my video workflow using ffmpeg. I also researched essential human skills like trust and taste that remain vital in an AI-driven economy.
I explored multi-agent architectures, refined my AI coding workflows using MCP and Cursor, and experimented with GPT 4.1 prompting. I also learned handy uv and jq tricks while investigating application-specific LLM evaluations.