LLM Security Automation Isn’t a Drop-In Scanner Yet
Analysis of structural failure modes when using LLMs as security scanners in agentic workflows, with measurement ideas and evidence.
Analysis of structural failure modes when using LLMs as security scanners in agentic workflows, with measurement ideas and evidence.
Summary of a London summit session on developer tools Kiro, AWS Transform Custom, and AWS DevOps Agent for community enablement.
A blog post advocating for reading academic papers as a key learning method in tech, sharing personal experiences and tips.
Analysis of weak vs. strong enterprise AI rollouts, highlighting the importance of solid guidance and practical examples over vague mandates.
Web Weekly #190 covers CSS image-set, variable fonts, accessibility tips, and tech humor including running Firefox with 84k extensions.
Explores the rise of headless services for personal AI agents, with APIs replacing GUIs for better user experience.
Explores the rise of headless services for personal AI agents, APIs as UI, and impact on SaaS pricing.
Summary of Azure IaaS and Azure Local updates from April 2026, including sovereign cloud leadership, new Denmark region, and Ephemeral OS Disk preview.
An R package for mapping NYC geographies like Census Tracts and NTAs, with code examples.
A production-oriented playbook for migrating from Spring Boot 3.x to 4.0, covering EOL risks, CVE exposure, and Jackson 2 to 3 changes.
Comparing Playwright MCP and Claude Code's /chrome for browser automation, highlighting setup and maintenance differences.
A personal blog post about replacing Notion with Markdown files and git for note-taking, focusing on privacy and simplicity.
A developer rewrites their blog using Zine, a new static site generator, after moving from Jekyll and Hugo over 15 years.
A guide on shifting left in DevOps with automated checks before merging code to prevent bad code and ensure quality.
Explores making illegal states unrepresentable using static typing, comparing Python, Java, Kotlin, Rust, and Gleam with a pizza builder example.
Analysis of system prompt changes between Claude Opus 4.6 and 4.7, highlighting new tools, safety updates, and behavioral improvements.
Analysis of system prompt changes between Claude Opus 4.6 and 4.7, including new tools, safety updates, and behavioral improvements.
Analysis of Anthropic Mythos's impact on cybersecurity, debunking hype and examining real LLM capabilities in vulnerability detection.
A developer shares a personal history with AI coding tools like GitHub Copilot and Claude Code, exploring their benefits and ethical concerns.
Explores how AI enables replacing SaaS tools with custom-built solutions, forcing companies to rethink their value and defensibility.