DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
trajectory-sentinel v0.1.0: correlación de señales de defensa de agentes

trajectory-sentinel v0.1.0: correlación de señales de defensa de agentes

3
Comments
2 min read
goal-anchor v0.1.0: integridad de objetivo para agentes multi-paso

goal-anchor v0.1.0: integridad de objetivo para agentes multi-paso

3
Comments
2 min read
adi-shield v0.1.0: detección de inyección de prompt en 5 vectores

adi-shield v0.1.0: detección de inyección de prompt en 5 vectores

3
Comments
2 min read
scope-lib v0.1.0: evaluación de alcance para agentes de IA en 3 criterios

scope-lib v0.1.0: evaluación de alcance para agentes de IA en 3 criterios

3
Comments
2 min read
Want to keep using Fable 5? Teach Opus and Sonnet to "behave" like it.

Want to keep using Fable 5? Teach Opus and Sonnet to "behave" like it.

8
Comments 1
9 min read
AI Integration in Full-Stack Development How LLMs Are Reshaping the Way We Build Software

AI Integration in Full-Stack Development How LLMs Are Reshaping the Way We Build Software

Comments
7 min read
Your AI Agent Will Double-Charge on a Lost Response

Your AI Agent Will Double-Charge on a Lost Response

Comments
14 min read
Google Gemma 4: The Developer Shift Toward Local-First AI Models

Google Gemma 4: The Developer Shift Toward Local-First AI Models

Comments
1 min read
Where Do Your LLM API Keys Actually Live?

Isolating keys from compromised dependencies

Where Do Your LLM API Keys Actually Live?

80
Comments 36
13 min read
Your AI Skills Have Two Dials. Most Ship With One Turned Off.

Your AI Skills Have Two Dials. Most Ship With One Turned Off.

14
Comments 18
6 min read
RAG for developers who aren't AI engineers: what actually matters

RAG for developers who aren't AI engineers: what actually matters

Comments 1
8 min read
NVIDIA Blackwell Leads AgentPerf, the First Agentic-AI Infra Benchmark: Trajectory-Replay Benchmarking

NVIDIA Blackwell Leads AgentPerf, the First Agentic-AI Infra Benchmark: Trajectory-Replay Benchmarking

Comments
6 min read
The Complete Guide to Local LLM Inference Tools in July 2026: llama.cpp, Ollama, vLLM, SGLang, and Beyond

The Complete Guide to Local LLM Inference Tools in July 2026: llama.cpp, Ollama, vLLM, SGLang, and Beyond

2
Comments 1
14 min read
A 9-point eval gain vanished when we deduped train against test

A 9-point eval gain vanished when we deduped train against test

Comments
4 min read
I built an AI tool that saves 80% LLM costs & catches hallucinations (Open Source)

I built an AI tool that saves 80% LLM costs & catches hallucinations (Open Source)

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