models
Speculative decoding for faster code completion
Speculative decoding uses a small draft model to predict multiple tokens at once, then verifies them in parallel with a larger model to speed up code completion.
2026-08-218 min read
Goatfied blog
Benchmarks, deployment notes, and hard-won patterns
Developer-to-developer writing. No fluff. Just what worked, what failed, and what shipped.
Filter by category
Filter by tag
All#security#refactoring#open-source#models#deployment#benchmarks#agent-loop#self-hosted#gpu#infra#devex#debugging#apps#agents#planning#tools#benchmark#cursor#copilot#code-review#triage#automation#pull-requests#architecture#reliability#case-study#strategy#trust#onboarding#telemetry#ux#inline-diff#ghost-text#lsp#completion#context#sandboxing#secrets#prompting#testing#docs
models
Embedding models for code search: a practical comparison
We benchmarked five embedding models on code search tasks to compare retrieval accuracy, query latency, and resource requirements for finding functions and implementation patterns.
2026-08-208 min read
models
Building evaluation sets from your own codebase
Learn how to extract, filter, and structure evaluation sets from your repositories to test code-generation tools on the code your team actually writes.
2026-08-198 min read
models
Why small models win at completion and lose at refactoring
Small models excel at code completion due to shallow context needs but fail at refactoring that requires understanding dependencies across multiple files.
2026-08-188 min read
models
Routing between fast and smart models without users noticing
Learn how to dynamically route requests between fast and slow LLMs based on prompt complexity, cost, and context without degrading user experience.
2026-08-178 min read
models
Quantization tradeoffs for code models: what you actually lose
Quantized code models use less memory but lose capabilities unevenly across tasks—this post measures what actually breaks in syntax, types, and logic at 4-bit and 2-bit precision.
2026-08-168 min read
models
When fine-tuning beats RAG for code, and when it doesn't
Fine-tuning teaches models your codebase's consistent patterns while RAG injects context at runtime; each excels in different scenarios for code generation.
2026-08-158 min read