DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Langfuse v4 + Ollama: Open-Source Tracer for Local LLMs (no OTLP, no mocks)

Langfuse v4 + Ollama: Open-Source Tracer for Local LLMs (no OTLP, no mocks)

Comments
6 min read
Building Production RAG Pipelines: Practical Lessons

Building Production RAG Pipelines: Practical Lessons

Comments
5 min read
Apple-OpenAI Tensions, AI Code Debt, and GraphBit’s Deterministic Agents

Apple-OpenAI Tensions, AI Code Debt, and GraphBit’s Deterministic Agents

Comments
2 min read
How I Built a Unicode Sanitizer to Stop Hidden Prompt Injection Attacks

How I Built a Unicode Sanitizer to Stop Hidden Prompt Injection Attacks

Comments 1
4 min read
Why splitting storyboard from rendering beats one mega-prompt for AI comics

Why splitting storyboard from rendering beats one mega-prompt for AI comics

1
Comments
4 min read
Stop Logging Your Thoughts: Mapping Agentic Reasoning Traces to Custom JFR Events for Zero-Overhead Debugging

Stop Logging Your Thoughts: Mapping Agentic Reasoning Traces to Custom JFR Events for Zero-Overhead Debugging

Comments
2 min read
Day 7 - Dense Embedding - RAG

Day 7 - Dense Embedding - RAG

Comments
2 min read
How much does it really cost to use AI models for coding?

How much does it really cost to use AI models for coding?

Comments
4 min read
84. Fine-Tuning LLMs: Teaching Giants New Tricks

84. Fine-Tuning LLMs: Teaching Giants New Tricks

Comments
8 min read
Beyond the Token Price: Why I built a "Forensic Audit" suite for AI Founders

Beyond the Token Price: Why I built a "Forensic Audit" suite for AI Founders

Comments
1 min read
How Companies Actually Get Tiered Token Pricing (and Why You Probably Can't Yet)

How Companies Actually Get Tiered Token Pricing (and Why You Probably Can't Yet)

Comments
3 min read
Used RTX 3090 Buying Guide for Local LLM in 2026

Used RTX 3090 Buying Guide for Local LLM in 2026

Comments
7 min read
Where AI Coding Is Actually Headed (Not the Hype Version)

Where AI Coding Is Actually Headed (Not the Hype Version)

Comments 1
4 min read
Why we hardcoded 8 niche presets instead of letting GPT generate slide layouts

Why we hardcoded 8 niche presets instead of letting GPT generate slide layouts

Comments
2 min read
The Overlooked Costs of Your LLM API Calls

The Overlooked Costs of Your LLM API Calls

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