DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
The Best Vector Database in 2026: Qdrant vs Pinecone vs Weaviate vs Milvus vs pgvector

The Best Vector Database in 2026: Qdrant vs Pinecone vs Weaviate vs Milvus vs pgvector

1
Comments
7 min read
The agent gave the right answer and did the wrong thing

The agent gave the right answer and did the wrong thing

4
Comments 5
10 min read
Qwen3 4B vs 8B vs 14B for Writing Correction: 60 Local Ollama Responses on Windows

Qwen3 4B vs 8B vs 14B for Writing Correction: 60 Local Ollama Responses on Windows

Comments
5 min read
Building Production AI Systems(Part 1)

Building Production AI Systems(Part 1)

1
Comments
2 min read
Your Agent Loop Just Cost $1,000: Instrumenting Spring AI with OpenTelemetry GenAI Conventions

Your Agent Loop Just Cost $1,000: Instrumenting Spring AI with OpenTelemetry GenAI Conventions

Comments
2 min read
Solving the GPU Pinning Saga and Gemma's Meta-Commentary

Solving the GPU Pinning Saga and Gemma's Meta-Commentary

Comments
2 min read
Ship a Production RAG Chatbot in a Weekend with Claude, pgvector, and FastAPI

Ship a Production RAG Chatbot in a Weekend with Claude, pgvector, and FastAPI

Comments
6 min read
Sonnet 5 vs GLM-5.2 vs everyone: how to pick the cheapest LLM API in 2026

Sonnet 5 vs GLM-5.2 vs everyone: how to pick the cheapest LLM API in 2026

Comments
3 min read
The Maintenance Window I Didn't Know I Was Running

The Maintenance Window I Didn't Know I Was Running

Comments
7 min read
When Better Models Make Old Agent Workflows Worse

Good models fail on rigid scaffolds

When Better Models Make Old Agent Workflows Worse

13
Comments 22
8 min read
MCP Server Tutorial: Build Your Own AI Tools in 30 Minutes

MCP Server Tutorial: Build Your Own AI Tools in 30 Minutes

Comments
10 min read
My LLM app was fully traced. During an incident the trace was still useless.

My LLM app was fully traced. During an incident the trace was still useless.

8
Comments 3
5 min read
The 21,000-Token Typo: Where Agentic Coding Budgets Actually Die

The 21,000-Token Typo: Where Agentic Coding Budgets Actually Die

Comments 1
3 min read
Sematic Coherance

Sematic Coherance

Comments
3 min read
One Model to Think, Two to Build

One Model to Think, Two to Build

Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.