DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Building Production-Ready RAG Applications: A Practical Guide

Building Production-Ready RAG Applications: A Practical Guide

1
Comments
4 min read
Kimi K3 vs K2.6 vs Fable 5 vs GPT: the specs and real API pricing in one table

Kimi K3 vs K2.6 vs Fable 5 vs GPT: the specs and real API pricing in one table

Comments
2 min read
Your Agent Telemetry Ranks Your Routing Policy, Not Your Models

Your Agent Telemetry Ranks Your Routing Policy, Not Your Models

1
Comments 4
6 min read
Production Interceptors for Solon ReActAgent: Stop Loops, Retry Tools, Sanitize Observations, Stream Events

Production Interceptors for Solon ReActAgent: Stop Loops, Retry Tools, Sanitize Observations, Stream Events

Comments
5 min read
Google's Gemma 2 is here. It's a big deal for open models.

Google's Gemma 2 is here. It's a big deal for open models.

1
Comments
3 min read
Why Agent Orchestration Sucks and the Loop Wins

Why Agent Orchestration Sucks and the Loop Wins

Comments
11 min read
Building an MCP Server That Verifies Its Sources: Inside footnote-mcp

Building an MCP Server That Verifies Its Sources: Inside footnote-mcp

Comments 2
2 min read
When Should You /clear? A 1913 Inventory Formula Has the Answer

When Should You /clear? A 1913 Inventory Formula Has the Answer

Comments 1
9 min read
我讓一個 AI 拿 2000 塊台幣去股市,目標 30 天翻倍,這是第 0 天

我讓一個 AI 拿 2000 塊台幣去股市,目標 30 天翻倍,這是第 0 天

2
Comments
1 min read
Measure your retrieval default: our hybrid RRF lost to plain vector search

Measure your retrieval default: our hybrid RRF lost to plain vector search

Comments 1
3 min read
GPT-5.6 Sol yields 30-year math proof as METR flags severe evasion behaviors

GPT-5.6 Sol yields 30-year math proof as METR flags severe evasion behaviors

7
Comments
9 min read
Stop building AI that acts like an oracle. Build a scientific partner instead.

Stop building AI that acts like an oracle. Build a scientific partner instead.

Comments
2 min read
Your LLM didn't fail. Your application trusted it too much.

Your LLM didn't fail. Your application trusted it too much.

Comments
1 min read
GPT Live实时语音模型与人类情感交流的边界探索

GPT Live实时语音模型与人类情感交流的边界探索

Comments
2 min read
Why AI Memory Is an Architecture Problem, Not a Database Problem

Why AI Memory Is an Architecture Problem, Not a Database Problem

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