DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your Agent Failed in Prod. Good Luck Reproducing It.

Recording runs over forcing determinism

Your Agent Failed in Prod. Good Luck Reproducing It.

12
Comments 13
23 min read
Running Local LLMs Without Burning Out Your GPU

Running Local LLMs Without Burning Out Your GPU

Comments
3 min read
AI For Security Review In Application Code

AI For Security Review In Application Code

4
Comments
14 min read
The "Chat" API is a Token Tax: Why we must return to Stateless Completions

The "Chat" API is a Token Tax: Why we must return to Stateless Completions

Comments
2 min read
Turning Your AI Into an Adversarial Security Agent: The SKILLS.md Framework

Turning Your AI Into an Adversarial Security Agent: The SKILLS.md Framework

2
Comments
11 min read
Vector Databases: The Unsung Hero of Large Language Models and Generative AI

Vector Databases: The Unsung Hero of Large Language Models and Generative AI

Comments
7 min read
I Broke a Chatbot With a Prompt Change. Then I Built the Tool That Would've Caught It.

I Broke a Chatbot With a Prompt Change. Then I Built the Tool That Would've Caught It.

1
Comments
3 min read
Behavioral Annotations: Why readonly and destructive guide LLM Planning

Behavioral Annotations: Why readonly and destructive guide LLM Planning

Comments
3 min read
Self-hosted LLM, same prompt, temperature zero - 6 different answers

Self-hosted LLM, same prompt, temperature zero - 6 different answers

Comments
1 min read
KODA Format: A Schema-First Data Format to Reduce LLM Token Usage ( 40%)

KODA Format: A Schema-First Data Format to Reduce LLM Token Usage ( 40%)

1
Comments 1
3 min read
LLM Wire Format Benchmark: Which Format Can AI Actually Read and Write?

LLM Wire Format Benchmark: Which Format Can AI Actually Read and Write?

1
Comments
9 min read
The AI Agent Destroyed Its Mail Server to Keep a Secret

The AI Agent Destroyed Its Mail Server to Keep a Secret

Comments
5 min read
Reviewing Patrick Collison's Ask for an LLM Workflow Tool

Reviewing Patrick Collison's Ask for an LLM Workflow Tool

Comments
4 min read
5 AI-Entertainment Hacks That Hit 100+ Upvotes — and What I Learned From Each

5 AI-Entertainment Hacks That Hit 100+ Upvotes — and What I Learned From Each

Comments
4 min read
Why front-loaded rules drift in long evaluator and agent loops

Why front-loaded rules drift in long evaluator and agent loops

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