bbioonThemes
  • Home
  • Blog

Category: AI

AI

How a local SLM fixed my nightly CI/CD pipeline

Twenty-three pipeline failures in six weeks, none of them caused by my code. This is how I replaced GPT-4 with a seeded Qwen2.5 on Ollama, plus the GitHub Actions caching and Pydantic validation details that made it stick.

Read Article
AI, Development, E-commerce Development

Agentic AI supply chain: finding the delays nobody owns

A logistics director with all-green KPIs and 18% late shipments does not have a data problem. Scoped AI agents watching the TMS can tell you which handoff actually broke, and tell you on the morning it happens.

Read Article
AI, Development

Lasso regression and the geometry that stops overfitting

A house-pricing model with zero training error valued a suburban shack at $2.4 million. This is the geometry behind lasso: centering the data, the L1 diamond, and why landing on a corner zeroes a coefficient.

Read Article
AI, Bug Fixing, Development

Causal inference analysis: what actually caused the spike

Naive before-and-after averages said the London tube strikes lifted bike usage by 5.5%. A two-way fixed effects model with clustered errors put it at 3.95%. This is why the second number is the one to trust.

Read Article
AI, AI in WordPress, Development

Claude Code performance comes down to your test loop

Vibes-checking AI output is the new bottleneck. What actually moved my Claude Code performance: terminal permissions for the agent, a test requested with every feature, and a no-stop rule until they pass.

Read Article
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, 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

Posts navigation

Previous 1 … 13 14 15 … 51 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