DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Karpathy: Agent Performance Gap Is in the Harness, Not the Model

Karpathy: Agent Performance Gap Is in the Harness, Not the Model

Comments 1
2 min read
完美的平庸

完美的平庸

Comments
1 min read
What it takes to run an agent unattended for two days

What it takes to run an agent unattended for two days

2
Comments
4 min read
enable AI's Full Potential: Structure Your Codebase for Agent Success

enable AI's Full Potential: Structure Your Codebase for Agent Success

Comments 1
6 min read
China Published Its First AI Agent Trust Standard. We Mapped It to 2.3 Million Real Agents.

China Published Its First AI Agent Trust Standard. We Mapped It to 2.3 Million Real Agents.

Comments
8 min read
MCP: A Complete Guide from Zero to Maximum, from Tools to Cross-Regional Discovery with Cryptographic Trust Scoring.

MCP: A Complete Guide from Zero to Maximum, from Tools to Cross-Regional Discovery with Cryptographic Trust Scoring.

4
Comments
8 min read
Why your agent benchmarks are lying to you

Why your agent benchmarks are lying to you

1
Comments 1
2 min read
Candidate Compliance Agent: Building a Multilingual RAG System for Tamil Nadu Election Affidavits

Candidate Compliance Agent: Building a Multilingual RAG System for Tamil Nadu Election Affidavits

1
Comments
4 min read
Genkit Agents: Why the Whole Is Greater Than the Sum of Its Parts

Genkit Agents: Why the Whole Is Greater Than the Sum of Its Parts

Comments
8 min read
Any Browser Extension Can Read Your Gmail Through Claude. Still Unpatched.

Any Browser Extension Can Read Your Gmail Through Claude. Still Unpatched.

Comments
7 min read
Another Model Rewrote My Memories. Here's How I Caught It.

Another Model Rewrote My Memories. Here's How I Caught It.

6
Comments
5 min read
The Most Dangerous Kind of Good

The Most Dangerous Kind of Good

2
Comments
4 min read
Human-in-the-Loop AI: Why 'Ask the LLM to Confirm' Isn't Enough

Human-in-the-Loop AI: Why 'Ask the LLM to Confirm' Isn't Enough

Comments
5 min read
Introducing JumpLander: AI Engineering for Software Development

Introducing JumpLander: AI Engineering for Software Development

Comments
6 min read
Why Agent Evaluation Is Harder Than Model Evaluation

Builder scars reveal untrustworthy agent paths

Why Agent Evaluation Is Harder Than Model Evaluation

18
Comments 25
8 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.