DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Evaluating Agents With an LLM-as-Judge Harness (Without Kidding Yourself About It)

Evaluating Agents With an LLM-as-Judge Harness (Without Kidding Yourself About It)

Comments 1
5 min read
I red-teamed my own LLM security gateway in four passes. Here's every gap I found.

I red-teamed my own LLM security gateway in four passes. Here's every gap I found.

Comments 1
9 min read
AI Is Entering a Phase of Extreme Uncertainty

AI Is Entering a Phase of Extreme Uncertainty

1
Comments
3 min read
When AI can't read, it invents — but it still sees the shape

When AI can't read, it invents — but it still sees the shape

1
Comments 5
7 min read
ThinkGraph - Give Your LLM a 50% Accuracy Boost by Building a Fact Foundation First

ThinkGraph - Give Your LLM a 50% Accuracy Boost by Building a Fact Foundation First

Comments 1
2 min read
DGX Spark hitting 83 C under sustained Ollama load — solved by clock-locking via nvidia-smi -lgc

DGX Spark hitting 83 C under sustained Ollama load — solved by clock-locking via nvidia-smi -lgc

Comments
3 min read
From Neo4j Fundamentals to GraphRAG: 7 Things I Learned About Building Modern AI Agents

From Neo4j Fundamentals to GraphRAG: 7 Things I Learned About Building Modern AI Agents

Comments
2 min read
This will get you banned from your ChatGPT subscription

This will get you banned from your ChatGPT subscription

1
Comments 1
2 min read
Guía de Despliegue y Ejecución del Modelo Cogito-2.1

Guía de Despliegue y Ejecución del Modelo Cogito-2.1

Comments
3 min read
AI Metrics Baseline: Prove Your Feature Works Before Scaling It

AI Metrics Baseline: Prove Your Feature Works Before Scaling It

1
Comments
9 min read
Claude Sonnet 5 — จบงานได้เหมือน Opus แต่จ่ายแค่ราคา Sonnet

Claude Sonnet 5 — จบงานได้เหมือน Opus แต่จ่ายแค่ราคา Sonnet

Comments
2 min read
If AI writes code, what is our job now?

If AI writes code, what is our job now?

Comments
2 min read
The bug that took me four hours to find had nothing to do with the model

The bug that took me four hours to find had nothing to do with the model

1
Comments 1
2 min read
Your AI agent can refuse to leak a secret — and leak it anyway, in its "thinking"

Your AI agent can refuse to leak a secret — and leak it anyway, in its "thinking"

1
Comments
6 min read
# Securing API Tokens: Protecting Your AI Applications from Credential Leakage

# Securing API Tokens: Protecting Your AI Applications from Credential Leakage

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