Think Different by Jakub Jirák - Blog
-
Google Gemini: Debugging a production incident from a screenshot and a log bundle
A field-tested take on debugging a production incident from a screenshot and a log bundle with Google Gemini: what it rewards, where it breaks, and how to keep the workflow honest.
-
The Future of Displays: MicroLED, Holograms, and Glasses Instead of Monitors
Explore the future of display technology from MicroLED to holographic displays and AR glasses. Understand which technologies will transform how we see.
-
ChatGPT Codex: Scoping tasks tightly enough that the agent can finish in one pass
A field-tested take on scoping tasks tightly enough that the agent can finish in one pass with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
How Technology Is Transforming Education for the Next Generation
Explore how technology is reshaping education for Generation Alpha. Discover AI tutors, adaptive learning, VR classrooms, and the skills students need.
-
Claude Code: Using sub-agents for parallel research across a large codebase
A field-tested take on using sub-agents for parallel research across a large codebase with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Autonomous Cars: The Technical Dream vs Legislative Reality
Explore the gap between autonomous vehicle technology and the legal frameworks needed to deploy it. Understand why self-driving cars face regulatory.
-
GitHub Copilot: Pairing inline completion with a custom instructions file to enforce house style
A field-tested take on pairing inline completion with a custom instructions file to enforce house style with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.
-
Why Software Updates Matter More Than New Features
Discover why software updates are more critical than shiny new features. Learn how security patches, performance fixes, and maintenance releases protect.
-
Local LLMs with Ollama: Picking a local model for the specific task, not for the benchmark
A field-tested take on picking a local model for the specific task, not for the benchmark with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
Home Robotics: We're Closer Than We Think
Explore how home robotics has evolved beyond robot vacuums. Discover the current state of domestic robots, emerging technologies, and why practical home.
-
Agentic coding: Budgets as the only feature that stops a bad loop
A field-tested take on budgets as the only feature that stops a bad loop with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.