DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
"LLM Inference Optimization: The Line Item That Decides If Your AI Ships"

"LLM Inference Optimization: The Line Item That Decides If Your AI Ships"

Comments
2 min read
Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)

Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)

1
Comments
4 min read
Caching LLM responses is just content addressing

Caching LLM responses is just content addressing

Comments
5 min read
OpenRouter solved one problem. I still had four more

Unpredictable pricing hurts app builders

OpenRouter solved one problem. I still had four more

20
Comments 11
2 min read
The Loadout Pattern: Handing the Wheel to an Autonomous LLM

The Loadout Pattern: Handing the Wheel to an Autonomous LLM

Comments
10 min read
How We Reduced Our LLM API Costs by 60%: What Actually Worked

How We Reduced Our LLM API Costs by 60%: What Actually Worked

1
Comments
7 min read
How to Clean Search Results Before Sending Them to an LLM

How to Clean Search Results Before Sending Them to an LLM

3
Comments
10 min read
# Evaluating an AI agent is not evaluating an LLM call:

# Evaluating an AI agent is not evaluating an LLM call:

Comments
3 min read
Active Working Memory: The RAM of Agentic Systems

Readers debate non-deterministic assembly

Active Working Memory: The RAM of Agentic Systems

11
Comments 8
5 min read
How I Built a Persona Chat Agent and Fought Hallucination — A RAG Story

How I Built a Persona Chat Agent and Fought Hallucination — A RAG Story

Comments
6 min read
[IBM-Tech] 提示词恶意软件杀伤链(The Promptware Kill Chain)剖析

[IBM-Tech] 提示词恶意软件杀伤链(The Promptware Kill Chain)剖析

Comments
1 min read
Why your AI coding agent ships confident, slightly-wrong code (and why rewording the prompt never fixes it)

Why your AI coding agent ships confident, slightly-wrong code (and why rewording the prompt never fixes it)

Comments
4 min read
LLM Function Calling: The Complete Guide for Building AI Tools

LLM Function Calling: The Complete Guide for Building AI Tools

Comments
3 min read
The End of "One-Shot AI": Why Context Engineering Is Replacing Prompt Engineering

The End of "One-Shot AI": Why Context Engineering Is Replacing Prompt Engineering

Comments
9 min read
Vidilearn: AI Knowledge Ingestion & Retrieval Gateway for LLMs, Agents, and MCP Servers

Vidilearn: AI Knowledge Ingestion & Retrieval Gateway for LLMs, Agents, and MCP Servers

2
Comments 2
1 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.