Modern Tech Stacks
Deep dives into modern frameworks, libraries, and best practices.
Appearance
Bockdev
Tech Stacks & Applied AI
Full stack developer exploring the intersection of modern tech and artificial intelligence.
Skip to content 
Structured Generation: Why AI Output Parsing No Longer Needs Regex
Learn how structured generation in LLMs lets you extract clean, typed JSON directly from AI models, eliminating the need for fragile regex parsers and post-processing hacks.
Structured generationLLM behaviorJSON output
The Consumption Spike: Managing the Hidden Compute Cost of Concurrency
Learn how concurrent workloads silently spike your compute costs, why traditional scaling metrics miss the problem, and how to detect, measure, and control concurrency-driven resource consumption in your systems.
ConcurrencyResource managementPerformance optimization
10 Ways Journalists and Content Creators Can Use AI Without Losing Their Voice
A working journalist shares 10 practical AI tools and workflows he uses daily, from beat monitoring and deep research to writing coaching and social media automation, while keeping human judgment at the center of every story.
AI ToolsJournalismContent Creation
OpenAI Codex Best Practices: How to Get Better Results Faster
A practical guide to using OpenAI Codex more effectively, covering prompting, AGENTS.md setup, configuration, MCP integrations, skills, automations, and common mistakes to avoid.
ChatGPTCodexOpenAI
The Mechanics of Prompt Caching: How to Design Cost-Efficient AI State
Learn how prompt caching works in large language models, why it reduces API costs and latency, and how to design your prompts and system state to take full advantage of it.
ClaudeAnthropicPrompt CachingCost-Effective AI State
What's New in Claude Opus 4.8: Key Features and Changes
A clear breakdown of everything new in Claude Opus 4.8, including fast mode, mid-conversation system messages, lower prompt cache minimum, refusal stop details, and behavior improvements.
ClaudeClaude Opus 4.8Anthropic