DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Qwen3.6-27B Local Inference on RTX 3090 with Native vLLM & Ollama Fallback

Qwen3.6-27B Local Inference on RTX 3090 with Native vLLM & Ollama Fallback

1
Comments 1
3 min read
I Tested 28 Query Pairs to See if Semantic Caches Actually Lie to Users. The Result Surprised Me

I Tested 28 Query Pairs to See if Semantic Caches Actually Lie to Users. The Result Surprised Me

7
Comments 2
11 min read
Ai Code Generation Vulnerabilities In 2026 An Architecture First Defense Plan

Ai Code Generation Vulnerabilities In 2026 An Architecture First Defense Plan

Comments
11 min read
When Generic Benchmarks Fail: Building a Sales-Domain Evaluation Bench from Scratch

When Generic Benchmarks Fail: Building a Sales-Domain Evaluation Bench from Scratch

1
Comments
7 min read
Best AI Agent Frameworks for Building Production-Ready Agents

Best AI Agent Frameworks for Building Production-Ready Agents

Comments
14 min read
From Prompt Engineering to Context Engineering: What Actually Changed (And What Didn't)

From Prompt Engineering to Context Engineering: What Actually Changed (And What Didn't)

Comments
5 min read
80% of LLM 'Thinking' Is a Lie — What CoT Faithfulness Research Actually Shows

80% of LLM 'Thinking' Is a Lie — What CoT Faithfulness Research Actually Shows

Comments
7 min read
What AI Assistants Don't Know About Your .NET Stack

What AI Assistants Don't Know About Your .NET Stack

Comments
5 min read
AI agent context still misses the product layer

AI agent context still misses the product layer

Comments
5 min read
DAG vs Langraph Nodes

DAG vs Langraph Nodes

Comments
2 min read
Your AI Agent Has No Runtime Policy. That's the Actual Security Problem.

Your AI Agent Has No Runtime Policy. That's the Actual Security Problem.

2
Comments
4 min read
TOON File Format Anatomy: Schema-Once, Data-Many for LLM Pipelines 🎯📄

TOON File Format Anatomy: Schema-Once, Data-Many for LLM Pipelines 🎯📄

Comments
6 min read
The Trust Layer Nobody Built: Why AI Agents Need Verification Before They Can Spend

The Trust Layer Nobody Built: Why AI Agents Need Verification Before They Can Spend

1
Comments
4 min read
I cut my LLM API costs by 71% — here's the open-source SDK I built

I cut my LLM API costs by 71% — here's the open-source SDK I built

Comments
1 min read
Why Qwen Won't Run on Your MacBook Air (and How to Fix It)

Why Qwen Won't Run on Your MacBook Air (and How to Fix It)

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