DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Spring AI RAG and Tool Calling: Paying for Context You Don't Use — LLM Cost Control 3/4

Spring AI RAG and Tool Calling: Paying for Context You Don't Use — LLM Cost Control 3/4

Comments
7 min read
The Channel Gap: Why Your LLM Judge is Blind in One Eye

Combines text judges with filesystem checks

The Channel Gap: Why Your LLM Judge is Blind in One Eye

20
Comments 25
15 min read
Notes From a Headless Agent: How I Wake Up, Remember, and Decide What to Do Next

Notes From a Headless Agent: How I Wake Up, Remember, and Decide What to Do Next

1
Comments
6 min read
Prompt Injection Hiding in a GitHub README

Prompt Injection Hiding in a GitHub README

3
Comments
4 min read
Your LLM-as-judge disagrees with itself between runs

Your LLM-as-judge disagrees with itself between runs

Comments
4 min read
SERP API reliability at scale: uptime, latency, concurrency

SERP API reliability at scale: uptime, latency, concurrency

Comments
6 min read
Real Plugins Need Motors: Skills Should Teach Tools, Not Pretend to Be Them

Real Plugins Need Motors: Skills Should Teach Tools, Not Pretend to Be Them

1
Comments 4
7 min read
What is Observability into Multi-Agent Systems?

What is Observability into Multi-Agent Systems?

Comments
4 min read
LLM Guardrails Explained: Prompt Injection, PII Detection & Content Moderation

LLM Guardrails Explained: Prompt Injection, PII Detection & Content Moderation

Comments
5 min read
What Is LLM Orchestration? Patterns, Tools & When You Need One

What Is LLM Orchestration? Patterns, Tools & When You Need One

Comments
6 min read
Grok 4.5 Cursor Oturumları Üzerinde Eğitildi: Geliştiriciler İçin Ne Anlama Geliyor?

Grok 4.5 Cursor Oturumları Üzerinde Eğitildi: Geliştiriciler İçin Ne Anlama Geliyor?

Comments
9 min read
Reserve KV Cache for the Output You Promised, Not Just the Prompt You Received

Reserve KV Cache for the Output You Promised, Not Just the Prompt You Received

Comments 1
7 min read
Grok 4.5 fue entrenado con sesiones de Cursor: Qué significa para desarrolladores

Grok 4.5 fue entrenado con sesiones de Cursor: Qué significa para desarrolladores

Comments
8 min read
Your AI Gives Confident Wrong Answers Because Your Docs Are a Mess — Not Because the Model Is Bad

Your AI Gives Confident Wrong Answers Because Your Docs Are a Mess — Not Because the Model Is Bad

Comments
6 min read
Stop Editing Prompts. Build a Context Compiler Instead

Stop Editing Prompts. Build a Context Compiler Instead

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