Tag: software-engineering
Page 10 of 48 • 518 posts total
-
Local LLMs with Ollama: Running evals locally before trusting a new model
A field-tested take on running evals locally before trusting a new model with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
Agentic coding: Planning outputs as the real product of the first turn
A field-tested take on planning outputs as the real product of the first turn with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
MCP servers: Testing MCP servers with a plain JSON-RPC client first
A field-tested take on testing MCP servers with a plain JSON-RPC client first with MCP servers: what it rewards, where it breaks, and how to keep the workflow honest.
-
AI coding workflows: Pair-with-AI rituals that survive a team of ten
A field-tested take on pair-with-AI rituals that survive a team of ten with AI coding workflows: what it rewards, where it breaks, and how to keep the workflow honest.
-
Prompt engineering for code: Difference between role prompts and persona cosplay
A field-tested take on the difference between role prompts and persona cosplay with Prompt engineering for code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cline and Roo Code: Routing cheap models for boilerplate, frontier models for design
A field-tested take on routing cheap models for boilerplate, frontier models for design with Cline and Roo Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
JetBrains AI Assistant: Scoping Junie tasks by module to keep review tractable
A field-tested take on scoping Junie tasks by module to keep review tractable with JetBrains AI Assistant: what it rewards, where it breaks, and how to keep the workflow honest.
-
Windsurf: Using write-mode sparingly to protect your muscle memory
A field-tested take on using write-mode sparingly to protect your muscle memory with Windsurf: what it rewards, where it breaks, and how to keep the workflow honest.
-
Cursor: Pairing tab with explicit intent comments to steer predictions
A field-tested take on pairing tab with explicit intent comments to steer predictions with Cursor: what it rewards, where it breaks, and how to keep the workflow honest.
-
Google Gemini: Auditing IAM policies with a million-token sweep over Terraform
A field-tested take on auditing IAM policies with a million-token sweep over Terraform with Google Gemini: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Parallelising bug-fix attempts and picking the cleanest patch
A field-tested take on parallelising bug-fix attempts and picking the cleanest patch with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.