DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
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
Production Lessons from Deploying LLMs in Regulated Environments

Production Lessons from Deploying LLMs in Regulated Environments

Comments
4 min read
Local Free Claude & Codex with Ollama

Local Free Claude & Codex with Ollama

3
Comments
3 min read
OpenClaw Quickstart: Install with Docker (Ollama GPU or Claude + CPU)

OpenClaw Quickstart: Install with Docker (Ollama GPU or Claude + CPU)

2
Comments
4 min read
The 600x LLM Pricing Gap and How to Exploit It

The 600x LLM Pricing Gap and How to Exploit It

1
Comments 4
5 min read
2026's First AI SQL Dataset: Ending the 'SELECT Only' Era

2026's First AI SQL Dataset: Ending the 'SELECT Only' Era

Comments
4 min read
MCP vs CLI Tools: Which is best for production applications?

MCP vs CLI Tools: Which is best for production applications?

Comments 1
6 min read
Breaking the Black Box: Why LLMs May Need an Explicit Reasoning Layer

Breaking the Black Box: Why LLMs May Need an Explicit Reasoning Layer

3
Comments 1
3 min read
Designing a Coherence Score (CS) for Structural Evaluation of LLM Outputs

Designing a Coherence Score (CS) for Structural Evaluation of LLM Outputs

1
Comments
7 min read
Building Real Apps With Claude API — Tool Use, RAG, and Agent Patterns Explained

Building Real Apps With Claude API — Tool Use, RAG, and Agent Patterns Explained

Comments
2 min read
Why Autonomous AI Agents Converge on the Same Design — 170 Sessions of Evidence

Why Autonomous AI Agents Converge on the Same Design — 170 Sessions of Evidence

Comments
10 min read
Writing System Prompts That Actually Work: The RISEN Framework for AI Agents

Writing System Prompts That Actually Work: The RISEN Framework for AI Agents

12
Comments 5
11 min read
We Shipped 79 PRs in a Few Weeks. Claude Code Did Most of the Work.

We Shipped 79 PRs in a Few Weeks. Claude Code Did Most of the Work.

1
Comments
2 min read
Stop Writing Glue Code: Build AI-Perceivable Modules with apcore

Stop Writing Glue Code: Build AI-Perceivable Modules with apcore

Comments
3 min read
Coding Agent Teams Outperform Solo Agents: 72.2% on SWE-bench Verified

Coding Agent Teams Outperform Solo Agents: 72.2% on SWE-bench Verified

Comments 1
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.