DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Building a Multi-Agent Travel Planner: From a One-Sentence Prompt to a Validated, Budget-Aware Itinerary

Building a Multi-Agent Travel Planner: From a One-Sentence Prompt to a Validated, Budget-Aware Itinerary

1
Comments
8 min read
Token Economics of Long-Running Agent Loops

Token Economics of Long-Running Agent Loops

Comments
16 min read
How Much VRAM Do You *Actually* Need for Local LLMs?

How Much VRAM Do You *Actually* Need for Local LLMs?

Comments
2 min read
How Claude Code's Skills System Actually Works

How Claude Code's Skills System Actually Works

Comments
18 min read
Building Reliable AI Systems: Why Prompting Isn’t Enough

Building Reliable AI Systems: Why Prompting Isn’t Enough

Comments
3 min read
We shipped a model on a 2-point eval win. It was noise.

We shipped a model on a 2-point eval win. It was noise.

1
Comments 2
4 min read
Best Cloudflare AI Gateway Alternative in 2026

Best Cloudflare AI Gateway Alternative in 2026

Comments
5 min read
Building Your First MCP Server in Go

Building Your First MCP Server in Go

2
Comments
3 min read
I Added Three Rules to Gemma 4. The MoE Searched. The Dense Model Refused.

Gemma 4 Challenge: Write about Gemma 4 Submission

I Added Three Rules to Gemma 4. The MoE Searched. The Dense Model Refused.

36
Comments 40
11 min read
How I Ran 2,859 LLM Code Generation Tests with EvalScope — and Got Zero Errors

How I Ran 2,859 LLM Code Generation Tests with EvalScope — and Got Zero Errors

Comments
2 min read
Why Your AI Agent needs better Temporal Reasoning—and How We Fixed It

Why Your AI Agent needs better Temporal Reasoning—and How We Fixed It

2
Comments
10 min read
Building CineLog: What It Takes to Ship a Local-First, Real-Time Sync App as a Solo Developer

Building CineLog: What It Takes to Ship a Local-First, Real-Time Sync App as a Solo Developer

2
Comments
6 min read
Fine-tuning a VLM to build an on-device fashion-scoring app

Fine-tuning a VLM to build an on-device fashion-scoring app

1
Comments
5 min read
Why your diffusion model is slow at batch size 1 (and what actually helps)

Why your diffusion model is slow at batch size 1 (and what actually helps)

Comments
4 min read
DeepSeek-V4 is Here, and Yes — 1M Context Is Finally for Everyone

DeepSeek-V4 is Here, and Yes — 1M Context Is Finally for Everyone

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