Treat AI advice, models and agent workflows as hypotheses: test them on your own work, mine your logs for evidence, and make verification part of the workflow.
Summary: Treat AI advice, models and agent workflows as hypotheses: test them on your own work, mine your logs for evidence, and make verification part of the workflow.
I updated my AI Advice page by mining two months of call transcripts with Gemini, Claude, and ChatGPT. The advice now covers how people, teams, and organizations operate in the agent era.
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 how I've used AI in my Tools in Data Science course: teaching through exams and prompts, designing assessment to make cheating pointless, building course content, and analyzing learning data.
I extracted AI advice from 400 call transcripts with Gemini Flash, combined the summaries, and used Gemini 3 Pro to synthesize them into a useful personal productivity guide for about $1.
I collected Google's AI tools across assistants, Workspace, developer platforms, creative apps, science, and models, marking the ones I find useful and highlighting Gemini, NotebookLM, Jules, and AI Studio.
