DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Three hackathon agents, one card-free API key: what I learned building on Qwen Cloud

Three hackathon agents, one card-free API key: what I learned building on Qwen Cloud

Comments
4 min read
AI Gateway Fees Compared: Who Marks Up Your Tokens?

AI Gateway Fees Compared: Who Marks Up Your Tokens?

1
Comments
4 min read
Pick your first AI model from evidence, not memory

Pick your first AI model from evidence, not memory

Comments
2 min read
Stop Making Your AI Agent Smarter. Make Its Context Smaller.

Stop Making Your AI Agent Smarter. Make Its Context Smaller.

Comments
3 min read
What I Learned Building a Real-Time AI Voice Agent

What I Learned Building a Real-Time AI Voice Agent

Comments
2 min read
Agent Leaderboards Measure Score. We Added Price.

Agent Leaderboards Measure Score. We Added Price.

Comments
5 min read
PageSpeed Insights Flagged My llms.txt. Here's What I Learned

PageSpeed Insights Flagged My llms.txt. Here's What I Learned

Comments
1 min read
I told the AI to sigh. It said the word "sigh."

I told the AI to sigh. It said the word "sigh."

Comments
2 min read
Why MCP Hookups, Not Just Models, enable Agent Potential in Production

Why MCP Hookups, Not Just Models, enable Agent Potential in Production

Comments
5 min read
Your AI Agent's Logs Are Lying to You: A 4-Field Schema That Actually Works

Your AI Agent's Logs Are Lying to You: A 4-Field Schema That Actually Works

Comments
5 min read
The Looping Principle: A Simple Mental Model for Understanding AI Agents

The Looping Principle: A Simple Mental Model for Understanding AI Agents

Comments
4 min read
Why Your Claude Code Orchestrator Silently Stops Dispatching Subagents

Why Your Claude Code Orchestrator Silently Stops Dispatching Subagents

1
Comments 1
4 min read
Seven Real Failures of an LLM Agent Operating a CAD Kernel (and How the Architecture Contained Them)

Seven Real Failures of an LLM Agent Operating a CAD Kernel (and How the Architecture Contained Them)

Comments 7
6 min read
This Smart-Home Agent Treats Its Own 1B Model as Untrusted Input

This Smart-Home Agent Treats Its Own 1B Model as Untrusted Input

Comments
3 min read
CPU vs GPU: Why Large Language Models Need GPUs — What Really Happens After You Press Enter?

CPU vs GPU: Why Large Language Models Need GPUs — What Really Happens After You Press Enter?

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