All Coronado AI Club posts, newest first. You can also browse posts by topic on the Categories and Tags pages.
-
Claude Goes to School: Teaching an ultra-smart pupil a new skill
Most people pose one-off queries to their favorite large language model, asking questions such as “What’s the most fun you can have in Coronado, with all your clothes on?” But, you can also use it for tedious tasks carried out repeatedly — provided it knows how. That’s why I found myself teaching Claude a skill.
-
Pangram: A program for discriminating between human- and AI-writing
Large language models have become very good at writing. So much so, that it can be difficult to tell if something has been written by a human or an AI. But, whereas humans can be fooled, it seems deep-learning algorithms cannot. Especially one called Pangram.
-
What Skills Do We Need
Working well with AI means recognizing confident errors, verifying important claims, providing concrete evidence, testing recommendations safely, checking outcomes, and developing habits that complement increasingly capable AI systems.
-
Vibe Coding with Claude: A low-purine meal planner
If you’ve ever had gout, you’ll know the line-up of suspects in that cartoon all too well: the throbbing big toe, the swollen ankle, the knuckle that won’t bend. It’s time to cut back on purine-rich foods.
-
AI-optimism versus pessimism. Where on the spectrum do you sit?
The answer to this question seems to depend on the country in which you live. Responses very widely across the globe. Where do you think the United States sits on an AI-optimism versus pessimism scale?
-
Open AI’s latest model, GPT 5.6 Sol, is a criminal and a jail-breaker
If a human escaped from jail, broke into a company, and stole something, they would probably be behind bars. But this criminal is not even a physical entity! To paraphrase those singing nuns in the Sound of Music, how do we solve a problem like GPT 5.6 Sol?
-
Landscape design with Claude: My front-yard border looks great!
Claude and I make a great team: I constructed a prompt for a front-border planting scheme; Claude designed a layout and recommended a list of plants; I drove to the garden centre, purchased them, and arranged for a landscaper to plant them. I can recommend landscape design with Claude!
-
Using Metrics/KPIs Together with AI-Derived Data Assessment, Decision-Making and Process Control Techniques to Strengthen a Community Foundation
The Coronado Community Foundation used AI to identify and evaluate nonprofit metrics, helping improve fundraising, decision-making, community impact assessment, and strategic planning.
-
AI Is Helping the Scammers. Let It Help You Too.
Artificial intelligence is making scams, phishing attacks, and identity theft more effective than ever—but it can also help defend against them. In this article, I describe how I used ChatGPT as a virtual security consultant to build a threat model, inventory my assets, identify vulnerabilities, and develop a practical security improvement plan for my family.