DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
LLM-as-judge tools compared: the question is not which one scores, it is which one you can trust

LLM-as-judge tools compared: the question is not which one scores, it is which one you can trust

2
Comments
2 min read
Want to Go Deeper?

Want to Go Deeper?

Comments
5 min read
Notification Hijacking: How WhatsApp and Slack Content Could Weaponize Google Gemini

Notification Hijacking: How WhatsApp and Slack Content Could Weaponize Google Gemini

1
Comments
5 min read
LLM integration with OpenRouter

LLM integration with OpenRouter

Comments
4 min read
Same Weights, Same Prompt, Different Triage Level

Same Weights, Same Prompt, Different Triage Level

Comments
11 min read
Building a Local-First Autonomous Agent from Scratch (LangGraph & Ollama)

Building a Local-First Autonomous Agent from Scratch (LangGraph & Ollama)

1
Comments
8 min read
Construire un Agent Autonome Local de zéro (LangGraph & Ollama)

Construire un Agent Autonome Local de zéro (LangGraph & Ollama)

Comments
10 min read
I built a local-first AI memory layer for LLMs in Rust (no cloud, no API keys)

I built a local-first AI memory layer for LLMs in Rust (no cloud, no API keys)

Comments
1 min read
How FinOps Teams Trace Per-Request AI Costs Through Multi-Tenant Gateways

How FinOps Teams Trace Per-Request AI Costs Through Multi-Tenant Gateways

Comments
2 min read
What makes AI API spend chargeback-safe by team/service?

What makes AI API spend chargeback-safe by team/service?

Comments
2 min read
Operator: cuando responder no basta

Operator: cuando responder no basta

Comments
7 min read
From Prompt to Production: Practical Lessons from Generative AI in .NET

From Prompt to Production: Practical Lessons from Generative AI in .NET

Comments
3 min read
Four ways production agents silently fail — and the physical patterns that prevent them (AOS v0.2)

Four ways production agents silently fail — and the physical patterns that prevent them (AOS v0.2)

Comments
5 min read
Six failures, a 32-minute TPU lie, and the moment a language model ignored my prompt on purpose

Six failures, a 32-minute TPU lie, and the moment a language model ignored my prompt on purpose

Comments
5 min read
The hidden cost of streaming LLMs: caches you can't use, bills you don't expect, and complexity you don't need

The hidden cost of streaming LLMs: caches you can't use, bills you don't expect, and complexity you don't need

Comments 1
11 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.