DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
MCP standard

MCP standard

Comments
2 min read
Can you save on LLM tokens using images instead of text?

Can you save on LLM tokens using images instead of text?

2
Comments 1
3 min read
From Fragile to Production-Ready: Reliable LLM Agents with Bedrock + Handit

From Fragile to Production-Ready: Reliable LLM Agents with Bedrock + Handit

Comments
4 min read
All Data and AI Weekly #209: 29 Sept 2025

All Data and AI Weekly #209: 29 Sept 2025

5
Comments
3 min read
Part II : Building My First Large Language Model from Scratch

Part II : Building My First Large Language Model from Scratch

Comments
4 min read
LLM Experimentation: Optimizing My Journaling Agent

LLM Experimentation: Optimizing My Journaling Agent

3
Comments 1
15 min read
The LLM-First Manifesto: From Prose to Programs

The LLM-First Manifesto: From Prose to Programs

1
Comments 1
5 min read
5 Best LLM Gateways for Scaling AI Applications in 2025

5 Best LLM Gateways for Scaling AI Applications in 2025

Comments
4 min read
Research Experience API を作りました!課題から論文 示唆 次アクションまで一気通貫

Research Experience API を作りました!課題から論文 示唆 次アクションまで一気通貫

Comments
1 min read
Test Automation Meets AI — Smarter QA with Playwright + LLMs

Test Automation Meets AI — Smarter QA with Playwright + LLMs

Comments
3 min read
Tool as Prompt: From LLM-First Docs to Teaching LLMs Domain Knowledge On The Fly

Tool as Prompt: From LLM-First Docs to Teaching LLMs Domain Knowledge On The Fly

Comments
3 min read
Less is More: 4 design patterns for building better MCP servers

Less is More: 4 design patterns for building better MCP servers

11
Comments
6 min read
How I Built a Private, Multi-User “Chat with Your Documents” App That Runs 100% Offline

How I Built a Private, Multi-User “Chat with Your Documents” App That Runs 100% Offline

Comments
7 min read
My Robot's Brain is a Markdown File (LLM-First,Tool as Prompt in action)

My Robot's Brain is a Markdown File (LLM-First,Tool as Prompt in action)

Comments
6 min read
From 70K to 2K Tokens: Optimizing SQL Generation with RAG Architecture

From 70K to 2K Tokens: Optimizing SQL Generation with RAG Architecture

15
Comments 1
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.