DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Beyond the Lone Cheetah: Architecture Patterns for Multi-Agent Prides in Real-World Ecosystems

Beyond the Lone Cheetah: Architecture Patterns for Multi-Agent Prides in Real-World Ecosystems

7
Comments 2
5 min read
Voice Sessions Now Know Who They Are. Here's What Changed.

Voice Sessions Now Know Who They Are. Here's What Changed.

1
Comments
2 min read
Why Integrating Multiple LLM Providers Gets Messy Fast

Why Integrating Multiple LLM Providers Gets Messy Fast

Comments
4 min read
Token Budgets Paper: Affine-Typed Budget Ownership

Token Budgets Paper: Affine-Typed Budget Ownership

Comments
6 min read
A voice agent is not a chatbot with a phone number

A voice agent is not a chatbot with a phone number

2
Comments 1
9 min read
Your AI Agent Keeps Failing After 50 Clean Demos, Stop Treating the LLM Like a Black Box

Your AI Agent Keeps Failing After 50 Clean Demos, Stop Treating the LLM Like a Black Box

Comments 1
4 min read
Subjectivation: A protocol to give LLMs a functional, responsible self

Subjectivation: A protocol to give LLMs a functional, responsible self

Comments
3 min read
Dashboards Don't Get Opened: Building a Weekly Lapse-Risk Pipeline That Pushes Work Instead of Waiting for Logins

Dashboards Don't Get Opened: Building a Weekly Lapse-Risk Pipeline That Pushes Work Instead of Waiting for Logins

Comments
3 min read
The MCP SDK's EventStore Lives in Memory. Here's What Happens When Your Server Restarts.

The MCP SDK's EventStore Lives in Memory. Here's What Happens When Your Server Restarts.

1
Comments
4 min read
What bothered me about the new SafeBreach Gemini paper wasn't the exploit

What bothered me about the new SafeBreach Gemini paper wasn't the exploit

1
Comments
4 min read
LLM-as-judge disagrees with itself between runs

LLM-as-judge disagrees with itself between runs

4
Comments 2
4 min read
Building a RAG System from Scratch — MCP: Exposing pgvector as a Reusable Tool Server

Building a RAG System from Scratch — MCP: Exposing pgvector as a Reusable Tool Server

Comments 3
6 min read
headroom, OpenRouter, MAI-Code-1-Flash — the week the agent runtime bill arrived

headroom, OpenRouter, MAI-Code-1-Flash — the week the agent runtime bill arrived

Comments
4 min read
Stop Paying for Failed AI Agent Retries

Stop Paying for Failed AI Agent Retries

Comments
1 min read
Beyond Prompts: Why Context Engineering Is the Real Future of Enterprise AI

Beyond Prompts: Why Context Engineering Is the Real Future of Enterprise AI

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