DEV Community

#llmtools

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your Agent Returned the Right Answer. That's Why It Was the Worst Possible Outcome.

Your Agent Returned the Right Answer. That's Why It Was the Worst Possible Outcome.

Comments 1
5 min read
I Spent a Week Watching My MCP Agents Get Hijacked by Tool Descriptions. Here's What I Built to Catch It.

I Spent a Week Watching My MCP Agents Get Hijacked by Tool Descriptions. Here's What I Built to Catch It.

Comments 1
5 min read
"Loop Engineering: How I Stopped My AI Agent From Reward-Hacking Its Own Quality Checks"

"Loop Engineering: How I Stopped My AI Agent From Reward-Hacking Its Own Quality Checks"

Comments
5 min read
I Ran 6 MCP Servers Behind One Agent. Here's What the Token Bill Actually Looked Like.

I Ran 6 MCP Servers Behind One Agent. Here's What the Token Bill Actually Looked Like.

Comments 1
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
My AI Agent Bottleneck Wasn't the Model. It Was the Architecture.

My AI Agent Bottleneck Wasn't the Model. It Was the Architecture.

Comments 1
4 min read
I Ran 1,000 LLM Evals Over 12 Months. Here's What Actually Moved the Needle

I Ran 1,000 LLM Evals Over 12 Months. Here's What Actually Moved the Needle

Comments
4 min read
The MCP Tax Hit 42,000 Tokens on a Single Server. Here's What I Did About It.

The MCP Tax Hit 42,000 Tokens on a Single Server. Here's What I Did About It.

Comments
4 min read
Your AI Agent Said 'Done.' Here's How I Found Out It Actually Failed Three Hours Later.

Your AI Agent Said 'Done.' Here's How I Found Out It Actually Failed Three Hours Later.

1
Comments
5 min read
The 50% Context Tax: Why Your AI Agent's Million-Token Window Is Burning Money

The 50% Context Tax: Why Your AI Agent's Million-Token Window Is Burning Money

Comments
4 min read
I Enabled MCP on My AI Coding Agent and My Token Bill Tripled: Here's the Math

I Enabled MCP on My AI Coding Agent and My Token Bill Tripled: Here's the Math

Comments
4 min read
I Cut My AI Agent's Token Bill by 62% in One Weekend. Here's the Receipts.

I Cut My AI Agent's Token Bill by 62% in One Weekend. Here's the Receipts.

Comments
5 min read
Gym Badges of Agentic Engineering (Part 1): Measuring Agent Success

Gym Badges of Agentic Engineering (Part 1): Measuring Agent Success

Comments
3 min read
Benchmarking LLMs for Coding in 2026: A Practical Guide

Benchmarking LLMs for Coding in 2026: A Practical Guide

Comments
3 min read
97M MCP Downloads and Still No Production Playbook: What I Learned the Hard Way

97M MCP Downloads and Still No Production Playbook: What I Learned the Hard Way

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