After a near-disaster, the agent powering Google Antigravity said something that surprised me. I asked it for more details, and eventually the agent, Claude Opus 4.5 (Thinking) offered to write this Power User Guide. I present it here with no validation or editing, just in case it has any merit. (Does it? I don’t know!)
Tag: LLM
I was vibe coding with Antigravity tonight, and I broke it in the most bizarre way. With the repo at this commit and with a clean working tree, I gave Gemini 3 Pro (High) this prompt:
Check out my git tags. Check out my git log! Ope, check out my @
CHANGELOG.md… And then write it.
For a few moments it seemed to chug along just fine, building a coherent Chain of Thought. Then it got weirder, and weirder.
This is article is the first installment in the Workflow Patterns for AI-Assisted Development series. To get notified when a new article is published, subscribe for free via email or RSS.
Domain Language Mining
Discover jargon from an unfamiliar field using LLMs to help you write better software.
I haven’t written PHP for over a decade. I haven’t even touched it since 2017. But in the spirit of legitimate peripheral participation, I asked a couple of LLMs to write a WordPress plugin for this blog. Within 15 minutes, I had a proof of concept from ChatGPT. Next, I got Claude to generate an even better version in one shot. I iterated to add a feature and said, “Hey! It compiles! Ship it!“
It was a fun experiment: a microcosm of failure, puzzle-solving, success, and iterative improvement.