DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Drift Detection for LLM Routing: Catching Silent Model Degradation

Drift Detection for LLM Routing: Catching Silent Model Degradation

Comments
8 min read
Building a RAG Pipeline From Scratch: What SmartQueue Taught Me About Retrieval

Building a RAG Pipeline From Scratch: What SmartQueue Taught Me About Retrieval

2
Comments
6 min read
Two queues for local-LLM fleets

Two queues for local-LLM fleets

Comments
7 min read
RAG-Fusion: Ask the Question Many Ways, Then Fuse the Ranks (RRF)

RAG-Fusion: Ask the Question Many Ways, Then Fuse the Ranks (RRF)

Comments
2 min read
What an LLM Actually Does: Predicting the Next Word, Explained

What an LLM Actually Does: Predicting the Next Word, Explained

Comments
2 min read
How I built a 3-provider LLM fallback system in production (and what actually broke)

How I built a 3-provider LLM fallback system in production (and what actually broke)

2
Comments
7 min read
Benchmarking LLMs for Coding in 2026: A Practical Guide

Benchmarking LLMs for Coding in 2026: A Practical Guide

Comments
3 min read
When Your AI Agent Goes Silent: The Failure Patterns Most Developers Miss

When Your AI Agent Goes Silent: The Failure Patterns Most Developers Miss

Comments
5 min read
AIchain Tools: Search, Conversion, Embeddings

AIchain Tools: Search, Conversion, Embeddings

Comments
6 min read
Unlocking Local LLM Power with Ollama: A Practical Guide

Unlocking Local LLM Power with Ollama: A Practical Guide

1
Comments
3 min read
Compiling the Process, Not the Code: a machine-checked workflow for coding agents

Compiling the Process, Not the Code: a machine-checked workflow for coding agents

Comments
10 min read
The Quantization Audit: Why Leaderboard Scores Lie About Local Agent Capabilities

The Quantization Audit: Why Leaderboard Scores Lie About Local Agent Capabilities

Comments 1
1 min read
Microsoft FastContext: a Repo-Explorer Subagent Cuts Coding-Agent Tokens 60%: Explorer-Subagent Context Offloading

Microsoft FastContext: a Repo-Explorer Subagent Cuts Coding-Agent Tokens 60%: Explorer-Subagent Context Offloading

Comments
7 min read
Claude AI da Anthropic: Conheça os Diferenciais Que Destacam Este Modelo [PT-BR]

Claude AI da Anthropic: Conheça os Diferenciais Que Destacam Este Modelo [PT-BR]

Comments
4 min read
Batch Processing vs Real-Time Inference: When to Use Each for Image Generation

Batch Processing vs Real-Time Inference: When to Use Each for Image Generation

Comments
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.