Goatfied blog

Benchmarks, deployment notes, and hard-won patterns

Developer-to-developer writing. No fluff. Just what worked, what failed, and what shipped.

open-source

Building a plugin ecosystem developers actually use

Learn how to design plugin systems where third-party extensions solve discrete problems, depend on stable contracts, and remain maintainable long-term.

2026-08-248 min read

open-source

Licensing AI-generated code: the questions nobody answers

Explore the unresolved legal questions around licensing AI-generated code when copyright law assumes human authorship and existing licenses don't address machine-created works.

2026-08-238 min read

open-source

What we learned open-sourcing our agent runtime

Goatfied open-sourced their agent runtime and discovered that external users exposed architectural assumptions through unexpected bug reports, feature requests, and integration needs.

2026-08-228 min read

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

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

deployment

Observability for AI coding assistants in production

Learn how to instrument AI coding assistants with LLM-specific observability: inference traces, quality metrics, token tracking, and model behavior correlation.

2026-08-148 min read

deployment

Multi-region deployment for latency-sensitive completion

Deploy LLM inference endpoints across regions to reduce code completion latency while managing model sync, consistency, and infrastructure costs.

2026-08-138 min read

Benchmarks, deployment notes, and hard-won patterns

Filter by category

Filter by tag

Building a plugin ecosystem developers actually use

Licensing AI-generated code: the questions nobody answers

What we learned open-sourcing our agent runtime

Speculative decoding for faster code completion

Embedding models for code search: a practical comparison

Building evaluation sets from your own codebase

Why small models win at completion and lose at refactoring

Routing between fast and smart models without users noticing

Quantization tradeoffs for code models: what you actually lose

When fine-tuning beats RAG for code, and when it doesn't

Observability for AI coding assistants in production

Multi-region deployment for latency-sensitive completion