close

DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
MCP After Year One — Six Design Lessons the Industry Is Still Learning

MCP After Year One — Six Design Lessons the Industry Is Still Learning

Image 2
Comments 1
8 min read
Agent memory v2 — seven rules after the poisoning

Agent memory v2 — seven rules after the poisoning

Image 2
Comments
10 min read
Integrating AI Detection and Humanization Features Into Your Application

Integrating AI Detection and Humanization Features Into Your Application

Comments
4 min read
Benchmarking 5 LLM providers on one eval set, no SDK per vendor

Benchmarking 5 LLM providers on one eval set, no SDK per vendor

Comments
4 min read
Streaming a LangGraph Agent as OpenAI-Compatible SSE (with a Thinking Panel)

Streaming a LangGraph Agent as OpenAI-Compatible SSE (with a Thinking Panel)

Comments 1
5 min read
You can't prevent prompt injection. So what do you actually do?

You can't prevent prompt injection. So what do you actually do?

Comments
3 min read
Build-time is where agent security is won or lost

Build-time is where agent security is won or lost

Comments
3 min read
When your agent does something bad, can you tell which agent did it?

When your agent does something bad, can you tell which agent did it?

Comments
4 min read
Two Patterns for Reducing LLM Costs in Data-Heavy RAG Apps

Two Patterns for Reducing LLM Costs in Data-Heavy RAG Apps

Image 1
Comments
6 min read
An AI agent exported a patient record. Your logs can't say who told it to.

An AI agent exported a patient record. Your logs can't say who told it to.

Comments
5 min read
How I A/B test LLM prompts without fooling myself

How I A/B test LLM prompts without fooling myself

Image 1
Comments
5 min read
AI Costs Are Cloud Costs Now: Why FinOps Is the New Playbook for AI Spend

AI Costs Are Cloud Costs Now: Why FinOps Is the New Playbook for AI Spend

Comments
8 min read
73% of AI-agent credential leaks trace back to one mundane thing: debug logging

73% of AI-agent credential leaks trace back to one mundane thing: debug logging

Comments
2 min read
Your AI agent is only as secure as the tools and agents it calls

Your AI agent is only as secure as the tools and agents it calls

Comments
4 min read
How Transformer Decoders Generate Text — From Causal Masking to Decoding

How Transformer Decoders Generate Text — From Causal Masking to Decoding

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