DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I Built a Skill Reviewer. Then I Ran It on Itself.

I Built a Skill Reviewer. Then I Ran It on Itself.

Comments
5 min read
I built a REST API that parses job descriptions into structured JSON using Claude Haiku, here's how...

I built a REST API that parses job descriptions into structured JSON using Claude Haiku, here's how...

Comments
2 min read
The Cinder Effect: Why Association, Not Accuracy, Separates Useful LLMs from the Rest

The Cinder Effect: Why Association, Not Accuracy, Separates Useful LLMs from the Rest

Comments
5 min read
Reliable LLM JSON Output: Few-Shot Prompting & Robust Parsing

Reliable LLM JSON Output: Few-Shot Prompting & Robust Parsing

Comments
6 min read
Building a Fully Local RAG System with Qdrant and Ollama

Building a Fully Local RAG System with Qdrant and Ollama

Comments
10 min read
Six Months in AI Feels Like Six Years: What Changed Since Q4 2025

Six Months in AI Feels Like Six Years: What Changed Since Q4 2025

Comments
2 min read
770 Experiments to Squeeze 30 tok/s Out of a 35B MoE Model on a $500 GPU

770 Experiments to Squeeze 30 tok/s Out of a 35B MoE Model on a $500 GPU

Comments
8 min read
3 Classifiers, 3 Answers: Why CoT Faithfulness Scores Are Meaningless

3 Classifiers, 3 Answers: Why CoT Faithfulness Scores Are Meaningless

Comments
6 min read
Autonomous AI Agents: Building Self-Running AI with Heartbeat, Cron & Memory

Autonomous AI Agents: Building Self-Running AI with Heartbeat, Cron & Memory

Comments
3 min read
Token Cost Optimization in Production LLMs: 3 Approaches With Real Numbers

Token Cost Optimization in Production LLMs: 3 Approaches With Real Numbers

Comments
4 min read
Why Claude's Free Tier Runs Out Faster Than You Think — The Token Math Nobody Explains

Why Claude's Free Tier Runs Out Faster Than You Think — The Token Math Nobody Explains

Comments
8 min read
Parameter Count Is the Worst Way to Pick a Model on 8GB VRAM

Parameter Count Is the Worst Way to Pick a Model on 8GB VRAM

Comments
5 min read
Your AI Agent Spent $500 Overnight and Nobody Noticed

Your AI Agent Spent $500 Overnight and Nobody Noticed

Comments
3 min read
I tried every major LLM observability platform. Traceport changed how I think about AI gateways.

I tried every major LLM observability platform. Traceport changed how I think about AI gateways.

Comments
4 min read
Top LLM Gateways That Support Semantic Caching in 2026

Top LLM Gateways That Support Semantic Caching in 2026

5
Comments
8 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.