DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Solving Tool Integration and Orchestration in AI Agents with MCP

Solving Tool Integration and Orchestration in AI Agents with MCP

1
Comments
3 min read
numasec Wants to Be the Claude Code of Penetration Testing

numasec Wants to Be the Claude Code of Penetration Testing

Comments
5 min read
RAG vs. Agent Memory vs. LLM Wiki: A Practical Comparison

RAG vs. Agent Memory vs. LLM Wiki: A Practical Comparison

6
Comments 3
8 min read
I Was Paying Anthropic to Read CSS Class Names

I Was Paying Anthropic to Read CSS Class Names

14
Comments 2
8 min read
The Rise of Inference Optimization: The Real LLM Infra Trend Shaping 2026

The Rise of Inference Optimization: The Real LLM Infra Trend Shaping 2026

2
Comments 5
3 min read
Stop Sending Raw PII to Your LLM

Stop Sending Raw PII to Your LLM

Comments
2 min read
Xoul - Building a Local AI Agent Platform with Small LLMs: The Walls of Tool Calling and Practical Solutions

Xoul - Building a Local AI Agent Platform with Small LLMs: The Walls of Tool Calling and Practical Solutions

Comments
3 min read
Cloudflare Workers HTML to Markdown on the Free Plan

Cloudflare Workers HTML to Markdown on the Free Plan

6
Comments 1
5 min read
TraceMind v2 — I added hallucination detection and A/B testing to my open-source LLM eval platform

Separate claim extraction and verification

TraceMind v2 — I added hallucination detection and A/B testing to my open-source LLM eval platform

23
Comments 9
2 min read
Defluffer promete -45% en tokens. Yo medí el costo semántico del ahorro y es incómodo

Defluffer promete -45% en tokens. Yo medí el costo semántico del ahorro y es incómodo

Comments
9 min read
MCP Server & Client in Spring AI: Stop Coupling Tools to Your AI Host

MCP Server & Client in Spring AI: Stop Coupling Tools to Your AI Host

Comments
5 min read
Bot Abuse in AI APIs: Why Your LLM Endpoint Is a Target

Bot Abuse in AI APIs: Why Your LLM Endpoint Is a Target

1
Comments
4 min read
3 AI Agent Guardrail Failure Modes from the HN CTF

3 AI Agent Guardrail Failure Modes from the HN CTF

Comments
3 min read
I built a self-hosted LLM proxy that supports 12 providers (Claude, GPT-4o, Gemini, Ollama...)

I built a self-hosted LLM proxy that supports 12 providers (Claude, GPT-4o, Gemini, Ollama...)

Comments
2 min read
From Simple LLMs to Reliable AI Systems: Building Reflexion, Based Agents with LangGraph

From Simple LLMs to Reliable AI Systems: Building Reflexion, Based Agents with LangGraph

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