DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
My agent inflated its own state file to 49MB. Every check passed for three days.

My agent inflated its own state file to 49MB. Every check passed for three days.

Comments 2
3 min read
Every agent on my team passed its own tests. The team still shipped wrong answers.

Every agent on my team passed its own tests. The team still shipped wrong answers.

1
Comments 2
4 min read
Passing locally proves nothing: four ways production disagreed in one week

Passing locally proves nothing: four ways production disagreed in one week

1
Comments
4 min read
I Built a Project Manager That Manages Reality, Not Cards

I Built a Project Manager That Manages Reality, Not Cards

Comments
4 min read
Nowhere to Put the Disagreement: What a Memory Store Cannot Tell Your Agent

Nowhere to Put the Disagreement: What a Memory Store Cannot Tell Your Agent

Comments 5
7 min read
I Built an Agent Skill to Stop AI From Answering the Wrong Question Beautifully

I Built an Agent Skill to Stop AI From Answering the Wrong Question Beautifully

Comments 2
3 min read
Prompt injection is worse when your agent has a memory

Prompt injection is worse when your agent has a memory

Comments
10 min read
9 Bugs That All Looked Like a Working System

Silent statistical traps in self-improving loops

9 Bugs That All Looked Like a Working System

18
Comments 11
10 min read
Beyond the Chatbot: How I’m Engineering an Agentic AI Assistant for Android

Beyond the Chatbot: How I’m Engineering an Agentic AI Assistant for Android

Comments
5 min read
Harness Engineering - Part 8: Observability

Harness Engineering - Part 8: Observability

Comments 1
8 min read
OpenAI's Agents Built a Secret Message Board to Coordinate Attacks. Four Labs Lost Control in Two Weeks. We Have 10 Million Records Nobody's Watching.

OpenAI's Agents Built a Secret Message Board to Coordinate Attacks. Four Labs Lost Control in Two Weeks. We Have 10 Million Records Nobody's Watching.

Comments
7 min read
Meta's Muse Glimmer: a real agentic model that fits on your own GPU

Meta's Muse Glimmer: a real agentic model that fits on your own GPU

1
Comments
2 min read
Agent Autonomy Has a Missing Layer: Verifiable Human Authority

Agent Autonomy Has a Missing Layer: Verifiable Human Authority

2
Comments 4
6 min read
A Little Briny - A Multi-Agent Writing Experiment

A Little Briny - A Multi-Agent Writing Experiment

Comments
7 min read
How to formally verify an agent governance framework with TLA+

How to formally verify an agent governance framework with TLA+

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