Tag: software-engineering
Page 6 of 48 • 518 posts total
-
Google Gemini: Keeping answers tight with explicit output contracts
A field-tested take on keeping answers tight with explicit output contracts with Google Gemini: what it rewards, where it breaks, and how to keep the workflow honest.
-
Why Copy-Paste Is the Biggest Enemy of Sustainable Code
Discover why copy-paste programming destroys code maintainability. Learn the real costs of duplication, when it's actually acceptable, and practical.
-
ChatGPT Codex: Treating Codex as a junior engineer with an infinite patience budget
A field-tested take on treating Codex as a junior engineer with an infinite patience budget with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
Claude Code: Diffing agent output against main before you trust a single file
A field-tested take on diffing agent output against main before you trust a single file with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
GitHub Copilot: Leaning on Copilot Edits for multi-file, reviewable diffs instead of raw chat
A field-tested take on leaning on Copilot Edits for multi-file, reviewable diffs instead of raw chat with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.
-
Local LLMs with Ollama: Caching embeddings locally for a private retrieval layer
A field-tested take on caching embeddings locally for a private retrieval layer with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
Agentic coding: Honest case for agents that only suggest
A field-tested take on the honest case for agents that only suggest with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
MCP servers: Why your wiki should probably be an MCP resource
A field-tested take on why your wiki should probably be an MCP resource with MCP servers: what it rewards, where it breaks, and how to keep the workflow honest.
-
AI coding workflows: Writing acceptance tests first, agents second
A field-tested take on writing acceptance tests first, agents second with AI coding workflows: what it rewards, where it breaks, and how to keep the workflow honest.
-
Prompt engineering for code: Diffing prompts the way you diff code
A field-tested take on diffing prompts the way you diff code with Prompt engineering for code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cline and Roo Code: Why open-source agents are a better teacher than closed ones
A field-tested take on why open-source agents are a better teacher than closed ones with Cline and Roo Code: what it rewards, where it breaks, and how to keep the workflow honest.