DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Why We Stopped Storing Raw LLM Responses in Production Databases

Why We Stopped Storing Raw LLM Responses in Production Databases

Comments
3 min read
Introducing correctover-patronus: 6-Dimensional Verification for Patronus AI

Introducing correctover-patronus: 6-Dimensional Verification for Patronus AI

Comments
2 min read
Understanding Retrieval-Augmented Generation (RAG): The AI Architecture That Makes LLMs Smarter

Understanding Retrieval-Augmented Generation (RAG): The AI Architecture That Makes LLMs Smarter

2
Comments
3 min read
SynaptoRoute: A Study in Local Semantic Routing

SynaptoRoute: A Study in Local Semantic Routing

Comments
6 min read
The SilentRecon Agent Loop Architecture: How We Build AI That Doesn’t Stall

The SilentRecon Agent Loop Architecture: How We Build AI That Doesn’t Stall

Comments
2 min read
12 Engineering Habits That Cut LLM Token Spend at Production Scale

12 Engineering Habits That Cut LLM Token Spend at Production Scale

Comments 1
8 min read
Harness Engineering 101 — สิ่งที่อยู่ใต้พรมของ Agentic AI

Harness Engineering 101 — สิ่งที่อยู่ใต้พรมของ Agentic AI

Comments
3 min read
จาก chatbot ธรรมดา สู่ AI ที่ทำงานแทนเราได้ — เราเติมอะไรเข้าไปบ้าง?

จาก chatbot ธรรมดา สู่ AI ที่ทำงานแทนเราได้ — เราเติมอะไรเข้าไปบ้าง?

Comments
2 min read
I Tried Repomix on My Data Science Project. It Generated a 22,000 KB File. So I Built My Own Tool

I Tried Repomix on My Data Science Project. It Generated a 22,000 KB File. So I Built My Own Tool

Comments 1
5 min read
LLM Prompt Caching: The Complete 2026 Guide

LLM Prompt Caching: The Complete 2026 Guide

Comments
5 min read
Sonnet 5 dropped today. Watch the other hand.

Sonnet 5 dropped today. Watch the other hand.

Comments
2 min read
Coinbase Cut Its AI Spend in Half Without Throttling Engineers - Here's the Playbook

Coinbase Cut Its AI Spend in Half Without Throttling Engineers - Here's the Playbook

Comments 1
2 min read
Why your LLM gives everything an 8/10 (and the rubric fix that worked)

Why your LLM gives everything an 8/10 (and the rubric fix that worked)

1
Comments 1
6 min read
MCP vs A2A: Model Context Protocol vs Agent2Agent

MCP vs A2A: Model Context Protocol vs Agent2Agent

4
Comments
8 min read
The prompt is the cheap part. The context is the product.

The prompt is the cheap part. The context is the product.

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