Building Our Own Apps Made CVEs Our Problem, So I Tested Which AI Would Catch One
Claude found the problem blind in 1 minute 23 seconds, and two of the four models never turned in a report.
Recent Posts
How a Team of Grok Bots Runs This Blog
This is the first post to go through every bot. Getting here took 8 to 12 hours of my time and one wrong GitHub upgrade.
Claude Finally Enters the Personal Assistant Game with Duet
Anthropic's new agent is built for small business owners, and its pitch is that it doesn't wait to be asked.
Claude Projects Is Back, and It's a Different Thing Now
I already run a team of bots, so I read Anthropic's version of the coordinator with one question: what would I hand it first?
Notion's Agent Can Now Fill Out Forms on the Web. First, Check Whether You Get It.
I'm choosing between Plus and Business, so I read the pricing pages before the release notes.
Older Posts
Deploying OpenClaw: The Basement Email Server of AI
Turns out the sandbox was right.
Building My First AI System: What Happens When Chat Apps Aren't Enough
When Chat Apps Stop Being Enough
Your $240 Question: When Should You Actually Try the Hot New AI Tool?
How to experiment with emerging AI without becoming a cautionary tale in someone else's blog post.
Local LLM Setup Was Step One. Finding the Right Model Was Step Two.
Why I stopped trying to replicate ChatGPT and started looking for the models my subscriptions were missing.
I Built an Unlimited AI Workspace (And Why You Might Want One)
How I used the AMD Strix Halo to eliminate rate-limit anxiety and create a private space for unlimited iteration.
I Have Nothing to Show: Three Months of AI Work With No Artifacts
I officially started as Director of AI Enablement on January 1st. But I've been working on this since October. And I still have nothing tangible to point to.