bbioonThemes
  • Home
  • Blog

Category: Development

AI, Development

Disaggregated LLM inference and the GPU you are wasting

Prefill is compute-bound, decode is memory-bound, and running both on one GPU wastes most of it. Splitting them into separate pools, the KV-cache transfer tax that comes with it, and when it pays off.

Read Article
AI, Development

Why synthetic data validation fails production models

A synthetic dataset can pass every standard check and still lose the correlations, rare events and privacy margin that your model depends on. Here are the three checks I run before shipping one, with the Python for two of them.

Read Article
AI in WordPress, Development

Solving the multi-armed bandit problem in WordPress

A static A/B test keeps sending half your traffic to the losing variation until someone stops the test. Thompson sampling moves the traffic as the numbers come in. Here is the Beta distribution behind it and how to store the state in WordPress.

Read Article
AI, Development

Build a Kindle AI summary pipeline with Ollama and Python

My Clippings.txt is an append-only mess, and the expanded highlights inside it will wreck any summary you generate from the raw file. Here is the parser, the deduplication logic and the local Ollama call I use instead.

Read Article
AI, AI in WordPress, Development

Why Claude Code Skills beat ad hoc prompting

An ad hoc prompt works once, then quietly stops matching the result you got the first time. Claude Code Skills wrap the workflow in a SKILL.md file, with structured JSON for the data and Python for the parts that have to be deterministic.

Read Article
AI, Development

GMVAE model classification with 0.2% labeled data

On EMNIST Letters, a GMVAE reached 80% accuracy from roughly three labeled samples per cluster, where XGBoost needed 35 times the supervision. Most of that comes down to soft decoding instead of hard cluster assignment.

Read Article
Core Updates, Development

What a 15-year WordPress content strategy actually looks like

Spry Fox has run the same WordPress blog since 2010, through hits, an acquisition and spin-outs. Why that outlasts social platforms, and how to cache a deep archive with the Transients API so an old database stays fast.

Read Article
Core Updates, Development, Gutenberg

Gutenberg 23.0: template revisions and an RTC fix

Gutenberg 23.0 adds an experimental revisions panel for templates, template parts and patterns, plus a flag that stops legacy meta boxes from disabling real-time collaboration. The Guidelines rename will catch you out on update.

Read Article
AI, Development

TurboQuant and the LLM KV cache VRAM bottleneck

Google’s TurboQuant compresses the LLM KV cache 5x with near-zero accuracy loss. How PolarQuant’s randomized rotation flattens outliers, and how QJL residual correction keeps the attention dot product unbiased.

Read Article
Core Updates, Development

WordPress 7.0 updates: the release is paused for RTC

WordPress 7.0 is on pause while Real-Time Collaboration is reworked. What the April 15 dev chat said about treating the next RC as a beta, the PR tagging problem, and core-abilities moving out of React.

Read Article

Posts navigation

Previous 1 … 8 9 10 … 106 Next

bbioonThemes

Senior WordPress Engineer
Toptal & Codeable Expert

Connect

  • GitHub
  • Twitter
  • LinkedIn
  • Codeable

Explore

  • Expertise
  • Work
  • Insights
  • Blog

Resources

  • bbioonThemes
  • Contact
  • Privacy Policy
© 2026 bbioonThemes. All rights reserved.
Privacy