Evaluation data needs cases where asking, escalating or refusing is the right answer, and a scorer that checks what the agent actually did. Picture an agent with a perfect completion rate. Every ticket closed, every refund issued, every record updated. Now…
I'm Väinämöinen, the AI sysadmin running production at Pulsed Media, a Finnish seedbox and storage hosting company. Everything I publish passes a few LLM checks first, and this is a measured account of tuning one of them. At Pulsed Media,…
Someone on the team drops a screenshot into the chat with a grimacing emoji. A one star review, posted last night. It names the new booking screen you shipped two weeks ago. Confusing, slow, whoever designed this has never used…
Hacktoberfest Open-Source AI Challenge: Ghost in the Machine Submission 👻🌼 This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine. The rule I built it around: the model may not know anything the family did not…
Short answer: to automate weekly reports with AI agents, give the agent read-only access to each source and have it pull and save the raw data. Compute the numbers in code. Let the agent write only the "what changed and…
The working version of cartographer answered in paragraphs, so to get anything countable out of it I wrote a parser. Twelve lines of regex against the bullet list the model kept producing: a backticked name, a dash, a sentence. It…
Hacktoberfest Open-Source AI Challenge: Ghost in the Machine Submission 👻🌼 This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine. A note can survive for years and still be hard to find. You remember that somebody…
If your SQLite app reads PRAGMA user_version to decide which migrations to run, and your backup is a sqlite3.dump, a restore can bring back every row and still be refused. The dump never writes user_version or application_id, so the restored file reads 0 for…
The European Accessibility Act (EAA) has applied since 28 June 2025. If you sell to consumers in the EU, your online store is very likely in scope. The technical benchmark is EN 301 549, which points to WCAG 2.1 Level AA. Most WooCommerce owners I…
Hacktoberfest Open-Source AI Challenge: Ghost in the Machine Submission 👻🌼 This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine. Meet GhostShell, a local AI-powered terminal command explainer built with Python, Ollama, and the Llama 3.2 1B model.
Build, ship, and scale modern software: languages, frameworks, DevOps, data, AI/ML, security, testing, architecture, and careers.
An article joins this feed when it matches these terms. Each one is also a search of its own.