DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why Cosine Similarity Fails in RAG (And What to Use Instead)

Why Cosine Similarity Fails in RAG (And What to Use Instead)

1
Comments
5 min read
Mastering RAG Evaluation: The Definitive Guide to Reliable AI

Mastering RAG Evaluation: The Definitive Guide to Reliable AI

1
Comments
3 min read
LLM, the compiler.

LLM, the compiler.

Comments
2 min read
Top 5 LLM Gateways for Production in 2026 (A Deep, Practical Comparison)

Top 5 LLM Gateways for Production in 2026 (A Deep, Practical Comparison)

77
Comments 10
7 min read
Agentic Workflows vs. Prompt Engineering: Which One Saves More Time?

Agentic Workflows vs. Prompt Engineering: Which One Saves More Time?

1
Comments
16 min read
Superpowers: The Technology to "Persuade" AI Agents—Why Psychological Principles Change Code Quality

Superpowers: The Technology to "Persuade" AI Agents—Why Psychological Principles Change Code Quality

Comments
5 min read
claude-switcher: The Concept of Piping Prompts into Unix

claude-switcher: The Concept of Piping Prompts into Unix

Comments
5 min read
Claude Prompt Leaks via Tool Abuse: Expert Blueprint to Secure AI Tooling in 2026

Claude Prompt Leaks via Tool Abuse: Expert Blueprint to Secure AI Tooling in 2026

Comments
6 min read
Why AI Output Fails Before Generation Ever Begins

Why AI Output Fails Before Generation Ever Begins

5
Comments 1
8 min read
Mastering Mistral API Costs: A Deep Dive into Pricing Models and Optimization Strategies

Mastering Mistral API Costs: A Deep Dive into Pricing Models and Optimization Strategies

Comments
6 min read
Developing with Claude Code? You should be using Checkmate!

Developing with Claude Code? You should be using Checkmate!

Comments
3 min read
Why Your MCP Server Sucks (And How to Fix It)

Why Your MCP Server Sucks (And How to Fix It)

2
Comments
5 min read
Building with A2UI: Extending the Expressiveness of AI Agent Interfaces

Building with A2UI: Extending the Expressiveness of AI Agent Interfaces

Comments
7 min read
Silent Degradation in LLM Systems: Detecting When Your AI Quietly Gets Worse

Silent Degradation in LLM Systems: Detecting When Your AI Quietly Gets Worse

2
Comments 1
5 min read
Don’t Trust Your Agents. Trust Your Boundary: a runtime authorization layer for LLM tool calls.

Don’t Trust Your Agents. Trust Your Boundary: a runtime authorization layer for LLM tool calls.

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