DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Prompt Versioning Is Not Optional in Production. Here Is How to Actually Do It.

Prompt Versioning Is Not Optional in Production. Here Is How to Actually Do It.

Comments
3 min read
How I Fixed Unpredictable AI Agents With Deterministic Monitoring

How I Fixed Unpredictable AI Agents With Deterministic Monitoring

15
Comments 6
7 min read
Study: stale documents are RAG poisoning without the attacker

Study: stale documents are RAG poisoning without the attacker

Comments
5 min read
Baidu Unlimited OCR Holds the KV Cache Constant for 40+ Pages: Reference Sliding Window Attention

Baidu Unlimited OCR Holds the KV Cache Constant for 40+ Pages: Reference Sliding Window Attention

Comments
8 min read
Why Positional Embeddings Matter — APE, RPE, and RoPE Explained for Developers

Why Positional Embeddings Matter — APE, RPE, and RoPE Explained for Developers

Comments
5 min read
AutoGen's hidden token tax: why a 3-agent chat costs 15 what you expect

AutoGen's hidden token tax: why a 3-agent chat costs 15 what you expect

Comments 1
5 min read
Your cache_read_input_tokens is zero. Here is what silently did it.

Your cache_read_input_tokens is zero. Here is what silently did it.

1
Comments 2
5 min read
How to Fine-Tune an LLM: A Complete Step-by-Step Guide

How to Fine-Tune an LLM: A Complete Step-by-Step Guide

Comments
8 min read
What Is the A2A Protocol? Agent Cards and Tasks Explained

What Is the A2A Protocol? Agent Cards and Tasks Explained

1
Comments
18 min read
Copilot for Word Will Copy Its Own Poison Into Every Document It Touches

Copilot for Word Will Copy Its Own Poison Into Every Document It Touches

3
Comments
5 min read
How to Reduce LLM Costs in Spring AI 2.0: 10 Practical Controls

How to Reduce LLM Costs in Spring AI 2.0: 10 Practical Controls

Comments
3 min read
Claude Code Costs, Act IV — The mistakes catalogue & cheat sheet

Claude Code Costs, Act IV — The mistakes catalogue & cheat sheet

1
Comments
7 min read
From RAG to Agentic AI. How I Added LangGraph to My Local RAG

From RAG to Agentic AI. How I Added LangGraph to My Local RAG

4
Comments 2
6 min read
Sml e Taleb

Sml e Taleb

Comments
4 min read
Modelo ou harness? O modelo define o teto, mas o harness decide o resultado

Modelo ou harness? O modelo define o teto, mas o harness decide o resultado

2
Comments
12 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.