Think Different by Jakub Jirák: posts, page 87 of 143
-
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.
-
LG's UltraFine 5K Reviewed: The Subtle Skills Hidden Behind the Pixels
A thoughtful, witty review of the LG UltraFine 5K, exploring how subtle skills like patience and perception reveal its understated brilliance. More than.
-
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.
-
The Farming of Hours: How to Cultivate Time Like a Field Instead of Burning It Like Fuel
Treat time as soil, not fuel. Learn how seasons, rotations cultivate sustainable productivity instead of burnout.
-
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.
-
The Fabric of Hours: Weaving Time Like Cloth Instead of Marching on a Timeline
Time is fabric, not a timeline. Discover how weaving threads, patterns enables you to create a resilient, colourful.
-
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.
-
The Economics of Hours - Treating Your Time Like Capital Instead of Loose Change
Treat time like capital. This article explores budgeting, ROI, risk, liquidity to transform time management into a.
-
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.
-
The Library of Hours: Cataloguing Time for Clarity and Control
Time is a library. Discover how shelves, genres, rare manuscripts can help you transform hours into wisdom.
-
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.