#ai
I feel dirty for liking customer support AI agents that actually give me a usable and working response within a few seconds.
The AI-crawler tax: who pays when bots are 57% of traffic
https://jorijn.com/en/blog/ai-crawler-tax-who-pays-when-bots-outnumber-humans/
GEO is still SEO: what Google actually said about AI search, llms.txt, and small business websites
https://jorijn.com/en/blog/geo-is-still-seo-ai-search-llms-txt-small-business-websites/
WordPress 7.0 put AI API Keys in the admin. Treat that as an operations policy, not a feature toggle.
https://jorijn.com/en/blog/wordpress-7-0-ai-api-keys-operations-policy/
Worried about Anthropic's new "Mythos" model?
You've probably seen it go by these past weeks: it supposedly found more than 10,000 vulnerabilities on its own, in software that runs just about everywhere. So I dug in, a deep dive heading into the weekend.
Mythos (and really the whole AI trend) rewards systems that are well maintained and punishes those that aren't.
The full deep dive is here: https://jorijn.com/en/blog/claude-mythos-ai-vulnerability-discovery-explained/
#cybersecurity #ai #infosec #anthropic #claude #security #mythos #jorijncom
WordPress 7.0 ships the AI Client. The Abilities API and MCP Adapter are what plugin developers should learn first.
https://jorijn.com/en/blog/wordpress-7-0-abilities-mcp-plugin-developers-learn-first/
I've been wondering where this #ai usage ends. It's been replacing junior and mid-level engineers, cutting the path to becoming a senior engineer.
Solving complex issues with your own brain is becoming less and less common. In the meantime, we're getting more dependent on these models to do the hard work for us.
I've been looking up research claiming that our ability to think deeply and our memory are rapidly deteriorating when we heavily use AI, and that scares the shit out of me.
WordPress Playground + MCP: AI coding agents meet a disposable WordPress environment
https://jorijn.com/en/blog/wordpress-playground-mcp-ai-coding-agents/
GitHub Actions agentic workflows: natural-language CI/CD meets reality
https://jorijn.com/en/blog/github-actions-agentic-workflows-natural-language-cicd/
I've been experimenting with MCP servers in Claude, which essentially allow you to connect data sources like Garmin and Strava to AI.
This week, I noticed that my heart rate was higher than usual at the same pace, so I asked Claude to analyze the data. To my surprise, it found a cause and supported its findings with ample data.
I'm not thrilled about needing to run more Z2 to recover from fatigue, but technologically, I find this _really_ cool.