DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Getting Started with Kiro Crew
qainsights profile

Getting Started with Kiro Crew

#ai #beginners #llm #aws
6
Comments 1
6 min read
Getting Started with ChromaDB : Vector Database
tarun6208 profile

Getting Started with ChromaDB : Vector Database

#ai #webdev #programming #llm
Comments
3 min read
DeepSeek V4 Flash Got Expensive. I Kept the Model and Cut the API Cost Anyway
sergeisolod profile

DeepSeek V4 Flash Got Expensive. I Kept the Model and Cut the API Cost Anyway

#ai #api #llm
Comments 1
10 min read
What Is an MCP Eval? Why Your Server Passes Every Test and Still Fails
rupa_tiwari_dd308948d710f profile

What Is an MCP Eval? Why Your Server Passes Every Test and Still Fails

#ai #mcp #testing #llm
14
Comments 3
9 min read
PIM-DBS: Back Up, Restore, and Verify Your AI Persona — a protocol born from a failed rescue
blacksmith5001 profile

PIM-DBS: Back Up, Restore, and Verify Your AI Persona — a protocol born from a failed rescue

#showdev #ai #llm #opensource
Comments
5 min read
"Hallucination" Is Three Different Bugs. We Keep Filing Them as One.
whetlan profile

"Hallucination" Is Three Different Bugs. We Keep Filing Them as One.

#discuss #ai #llm #programming
Comments
9 min read
Knowledge Graph vs Retrieval for Agent Memory: The Real Split Is What You Are Willing to Assert
izgorodin profile

Knowledge Graph vs Retrieval for Agent Memory: The Real Split Is What You Are Willing to Assert

#ai #agents #llm #architecture
Comments
6 min read
RAG Evaluation with RAGAs: Faithfulness, Context Recall, and Answer Relevance
michael_pham018 profile

RAG Evaluation with RAGAs: Faithfulness, Context Recall, and Answer Relevance

#ai #machinelearning #python #llm
Comments
7 min read
5 MCP pains that waste your tokens — and how I killed all 5 with a 50KB CLI
mcptokensaver profile

5 MCP pains that waste your tokens — and how I killed all 5 with a 50KB CLI

#mcp #ai #llm #optimization
1
Comments
2 min read
Models retire faster than operating systems
dsiacci profile

Models retire faster than operating systems

#ai #llm #architecture #nocode
5
Comments
3 min read
Quantizing MedGemma to INT4 (GPTQ/W4A16): Everything That Broke Along the Way
joteqthefirst profile

Quantizing MedGemma to INT4 (GPTQ/W4A16): Everything That Broke Along the Way

#machinelearning #llm #quantization #opensource
Comments
6 min read
Getting AIs to review each other was easy. The hard part was measuring whether I could trust the reviewer
ryosuke_matsuzaki_64cd24a profile

Getting AIs to review each other was easy. The hard part was measuring whether I could trust the reviewer

#ai #llm #softwareengineering #codereview
Comments
7 min read
Building a Cost-Aware LLM Router: Automatically Pick the Cheapest Model for Each Task
aidabbler profile

Building a Cost-Aware LLM Router: Automatically Pick the Cheapest Model for Each Task

#ai #api #architecture #llm
Comments
1 min read
Hardening Applications That Call LLMs: 16 Security Controls That Actually Matter
renolu profile

Hardening Applications That Call LLMs: 16 Security Controls That Actually Matter

#ai #security #llm #programming
Comments
4 min read
Stop Guessing JVM Bugs: Connect Claude Code to Spring Boot via Local MCP Actuator Servers
machinecodingmaster profile

Stop Guessing JVM Bugs: Connect Claude Code to Spring Boot via Local MCP Actuator Servers

#java #productivity #ai #llm
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.