DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
The cheapest LLM call is the one you don't make: a caching layer that actually pays off
xuanyi profile

The cheapest LLM call is the one you don't make: a caching layer that actually pays off

#llm #ai #costoptimization #tutorial
Comments
3 min read
I Gave My LLM an Exam. The Exam Author Lost 5 Times.
ramses203 profile

I Gave My LLM an Exam. The Exam Author Lost 5 Times.

#ai #llm #testing #programming
Comments
5 min read
My AI quality gate scored 40 images. Humor: 7, forty times.
booyaka101 profile

My AI quality gate scored 40 images. Humor: 7, forty times.

#ollama #ai #llm #machinelearning
Comments
5 min read
Prompt injection: your customer-facing AI is an attack surface
ranaharoon3222 profile

Prompt injection: your customer-facing AI is an attack surface

#ai #security #llm #typescript
Comments
7 min read
A 2-Token Prompt and a 39,966-Token Bill: Measuring What My Agent Actually Costs
enjoy_kumawat profile

A 2-Token Prompt and a 39,966-Token Bill: Measuring What My Agent Actually Costs

#ai #llm #claudecode #devtools
1
Comments
5 min read
How to Benchmark a Unified LLM API: Node.js Invoice Extraction Under Latency Limits
rivenpulse5812 profile

How to Benchmark a Unified LLM API: Node.js Invoice Extraction Under Latency Limits

#node #typescript #llm
Comments
7 min read
Ornith-1.0 is a clever open coding model. Ollama's tool-calling isn't ready for it.
mediblacksand_f0ea36c53fb profile

Ornith-1.0 is a clever open coding model. Ollama's tool-calling isn't ready for it.

#ai #ollama #opensource #llm
Comments
4 min read
Choosing the Right GPU for Your Model — A Sizing Method, Not a Guess
josef_doornink_930b2caf1c profile

Choosing the Right GPU for Your Model — A Sizing Method, Not a Guess

#ai #gpu #llm
Comments 1
9 min read
The Hottest AI Framework Right Now Has a Fatal Flaw Nobody Mentions
aibughunter profile

The Hottest AI Framework Right Now Has a Fatal Flaw Nobody Mentions

#aiagents #ai #llm #webdev
Comments
4 min read
🛡️ Arquitectura de Defensa para Agentes de IA: Cómo asegurar tus LLMs contra Prompt Injection, Tool-Poisoning y Fugitividad.
magopredator profile

🛡️ Arquitectura de Defensa para Agentes de IA: Cómo asegurar tus LLMs contra Prompt Injection, Tool-Poisoning y Fugitividad.

#ai #architecture #llm #security
Comments
3 min read
Your AI Remembers Everything. That’s the Problem.
mikeross27 profile

Your AI Remembers Everything. That’s the Problem.

#ai #agents #llm #programming
Comments 1
6 min read
Building Custom MCP Servers: Extending AI with Tools
3ni8ma profile

Building Custom MCP Servers: Extending AI with Tools

#mcp #aiagents #llm #tooling
1
Comments
12 min read
Your Legal Question Has an Address
jimmyknowslaw profile

Your Legal Question Has an Address

#ai #legal #llm #software
Comments
3 min read
Not Every LLM Needs vLLM: A Kubernetes Engineer's Guide to Serving Engines
the-persistent-engineer profile

Not Every LLM Needs vLLM: A Kubernetes Engineer's Guide to Serving Engines

#kubernetes #llm #ai #devops
Comments
12 min read
117 Ghost Errors: Anatomy of a Flaky AI Agent
jula-markova profile

117 Ghost Errors: Anatomy of a Flaky AI Agent

#ai #llm #debugging #programming
Comments
10 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.