How I get Claude Code to improve itself overnight
I stopped hand-holding Claude Code and gave it a nightly review instead: a self-reflection skill, a 2 AM cron job, and a rules file it edits itself. This is the setup I run on real WordPress work.
Category: AI
Unified agentic memory with lifecycle hooks and Neo4j
Every AI harness keeps its own memory, so moving from Cursor to Claude Code means starting from zero context. Here is the shared layer I build instead: lifecycle hooks writing into Neo4j, plus the batch job that turns raw events into notes.
WordPress Workspace for Mac: what the beta actually does
WordPress Workspace for Mac is in beta. It puts a site-aware agent, voice dictation and screenshot uploads on the desktop instead of in another browser tab, and it previews the Guidelines feature headed for Core.
Data wrangling with Pandas is still my default in 2026
Rust-based data libraries keep shipping, but Pandas still runs most of my production pipelines. Vectorized string operations, ast.literal_eval instead of eval, and the DataFrame constructor trick that beats df.apply(pd.Series) on big datasets.
Why recursive language models beat ReAct for long context
Recursive language models get a pointer to the data instead of having the whole thing pasted into the prompt. Why that beats ReAct and CodeAct on long-context work, and what it means for auditing a large WordPress codebase.
6 AI production trade-offs that show up after launch
Six trade-offs that decide whether an AI feature survives production: what a cheap API really costs at scale, why a complex model gets expensive 18 months later, and when batch inference beats real-time.
Credit scoring categorization: how to bin risk variables
Raw variables are rarely the best way to represent risk. How binning and Weight of Evidence keep a logistic regression stable and interpretable, and why missing income is a risk category of its own.
WordPress 7.0 features and what they mean for developers
WordPress 7.0 brings a provider-agnostic AI client, PHP-only block registration with autoRegister, and a minimum PHP 7.4. This is a practical walk through those changes, with code examples and where they help on real sites.
Why your AI coding assistant drifts into the wrong language
Mixing technical English tokens like run.py can push an AI coding assistant to drift in the embedding space, sometimes replying in Korean when prompted in Chinese. How task registers shape the behavior, and how to keep your prompts grounded.
Build an LLM evaluation system that catches hallucinations
A scoring layer that measures attribution and specificity, so you can catch confident hallucinations instead of trusting responses that just sound right. Includes the Python logic and a regression suite for CI.