Thinking in Loops: Finding the Frontier Without a Frontier Budget
Three days into scoring a legal benchmark, my tokens ran out. The fix wasn't a bigger budget or a better model — it was a different shape. On orchestration, loops, and reaching the frontier of what AI can do without a frontier budget.
My Agent Did the Legal Work. The Benchmark Gave It Zero.
Somewhere in my benchmark results sits a complete legal memorandum. Fifty-eight kilobytes of finished work: issues identified, analysis done,
Commentary: The Pitfalls of Seeking AI Advice From Lawyers
A sharp CNA commentary argues AI can't replace lawyers. It's aiming a very good argument at old technology — and missing the real threat.
Lawyers Are Building. Just Not On Each Other's Code.
Mike got 2,657 stars in eleven days and six merged pull requests. The LegalQuants directory has 112 lawyer-coders and one repo that cleared the bar — mine. Legal open source isn't a community yet. It's a federation of solo-author archipelagos.
From One Source to Three: When the Right Agent Showed Up
I've written about data.zeeker.sg for months without ever saying: go use it. Three databases now live. Here's the agent architecture that finally made solo ownership tractable enough to invite people in.
Word on Claude: The Lawyer's Greatest Legal Tech Tool Strikes Back
Claude for Word is here, and it's genuinely good. But the interface you work in shapes the thinking you do — and if you can't tell whether you're doing strategy or execution, you might be missing the forest for the trees.
OpenClaw Field Notes: A Lawyer Tries to Tame an Autonomous AI Agent
Turns out the hard part isn't prompt engineering. It's designing the harness — a problem most lawyers, even lawyer-coders, aren't equipped to solve yet.
Where Is My Work? — How AI Tools Quietly Fragment Your Files
I sent my laptop for repair and assumed everything was backed up. Then I opened my iPad to work and discovered how many places AI tools had quietly scattered my files.
AI Won't Replace You. Someone Who Decides Will.
The conventional AI-and-jobs conversation is stuck on the wrong question. AI can't practise intentionality — it resolves statistical patterns. That makes the human behind the prompt the entire moral equation.
From Draft to Final: What Changed in MinLaw's AI Guide (And What It Means for You)
I submitted feedback on MinLaw's draft AI guide expecting nothing. Six months later, the final guide adopted both recommendations near-verbatim. Here's what changed and what it means for solo counsel.
