DEV Community

#agents

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Your AI agent isn't hallucinating- it's reading garbage context

Your AI agent isn't hallucinating- it's reading garbage context

1
Comments 1
4 min read
Letting an agent write to my production CMS

Letting an agent write to my production CMS

2
Comments 2
7 min read
I Let an Agent Take Over an Account With Every Permission Check Green

Runnable proof shows session-split bypasses

I Let an Agent Take Over an Account With Every Permission Check Green

25
Comments 71
4 min read
The Amnesia Tax

The Amnesia Tax

1
Comments 1
6 min read
My 7/7 Gate Fell to One Admin Capability. A Second Witness Only Moved the Wall.

My 7/7 Gate Fell to One Admin Capability. A Second Witness Only Moved the Wall.

24
Comments 3
13 min read
Your Agent's Plan Isn't a Plan. It's a Post-Hoc Rationalization

Your Agent's Plan Isn't a Plan. It's a Post-Hoc Rationalization

Comments
5 min read
从"玩具"到"教材":一个500行AI框架的自我修养

从"玩具"到"教材":一个500行AI框架的自我修养

Comments
1 min read
LLMs on Consumer Hardware — Part 3: A Multi-Agent Setup with Hermes — Delegation and Early Failure Modes

LLMs on Consumer Hardware — Part 3: A Multi-Agent Setup with Hermes — Delegation and Early Failure Modes

Comments
5 min read
I expected pair programming with a Cloud Agent. I got a new hire.

I expected pair programming with a Cloud Agent. I got a new hire.

7
Comments
4 min read
How I Built an AI Voice Agent to Cut COD Returns by 40%

How I Built an AI Voice Agent to Cut COD Returns by 40%

5
Comments
4 min read
What Is an Agent Registry? (And What We Broke Before We Had One)

What Is an Agent Registry? (And What We Broke Before We Had One)

1
Comments
7 min read
Is your agent's "done" real? A 15-minute self-check before you trust it

Is your agent's "done" real? A 15-minute self-check before you trust it

6
Comments 58
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
How I Use Codex to Build Applications Without Losing Control

How I Use Codex to Build Applications Without Losing Control

1
Comments
9 min read
Your Agent's Deadline Is a Correctness Test, Not an SLO

Your Agent's Deadline Is a Correctness Test, Not an SLO

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