DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Two Pre-Registered Benchmarks for Audit-Native RAG: RAB (EU AI Act 10/12/19) + LRB (Time-Travel Retrieval)

Two Pre-Registered Benchmarks for Audit-Native RAG: RAB (EU AI Act 10/12/19) + LRB (Time-Travel Retrieval)

1
Comments
3 min read
OWASP Top 10 for LLMs: A Practitioner’s Implementation Guide

OWASP Top 10 for LLMs: A Practitioner’s Implementation Guide

Comments
9 min read
What is an LLM evaluation harness? A deep dive into lm-eval-harness

What is an LLM evaluation harness? A deep dive into lm-eval-harness

1
Comments
7 min read
Most RAG Problems Are Retrieval Problems. Here Are 8 Fixes That Worked for Me

Most RAG Problems Are Retrieval Problems. Here Are 8 Fixes That Worked for Me

1
Comments
4 min read
DeepClaude Merges Two AI Models Into One Agent Loop

DeepClaude Merges Two AI Models Into One Agent Loop

Comments
6 min read
XML Tags Don't Help Short Prompts — Here's When They Actually Matter (2026)

XML Tags Don't Help Short Prompts — Here's When They Actually Matter (2026)

Comments
4 min read
Building an MCP server — lessons from thunderbit-mcp

Building an MCP server — lessons from thunderbit-mcp

Comments 1
8 min read
ProxyFace: Give Your AI a Face & Emotions (100% Local, Zero Telemetry)

ProxyFace: Give Your AI a Face & Emotions (100% Local, Zero Telemetry)

Comments
2 min read
Why Prompts Fail in Production (and the 4 Failure Vectors)

Why Prompts Fail in Production (and the 4 Failure Vectors)

Comments 1
4 min read
DeepSeek V4, `llama.cpp` Q4_K_M, & Ollama Ryzen APU Guide Boost Local LLM

DeepSeek V4, `llama.cpp` Q4_K_M, & Ollama Ryzen APU Guide Boost Local LLM

Comments
3 min read
Beyond Keywords: Mastering HyDE for Smarter Retrieval đź§ 

Beyond Keywords: Mastering HyDE for Smarter Retrieval đź§ 

Comments
4 min read
LangChain ChromaDB Metadata Priority Injection — RAG Poisoning Vulnerability

LangChain ChromaDB Metadata Priority Injection — RAG Poisoning Vulnerability

Comments
1 min read
Structured output from LLMs: JSON mode, function calling, and grammar-constrained decoding

Structured output from LLMs: JSON mode, function calling, and grammar-constrained decoding

1
Comments
7 min read
Debugging confidently wrong answers from LLM-powered features

Debugging confidently wrong answers from LLM-powered features

Comments
4 min read
AI Cited a URL That Didn't Contain the Claim. I Built the Tooling to Measure How Often

AI Cited a URL That Didn't Contain the Claim. I Built the Tooling to Measure How Often

1
Comments
16 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.