DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The File Modification Boundary We Found After 12 ForgeFlow Projects

The File Modification Boundary We Found After 12 ForgeFlow Projects

Comments
8 min read
I version every prompt I send to Claude. Here's why.

I version every prompt I send to Claude. Here's why.

Comments
5 min read
Running a Fully-Local AI Agent on a Mac Studio, OpenClaw + Ollama + MLX

Running a Fully-Local AI Agent on a Mac Studio, OpenClaw + Ollama + MLX

2
Comments 2
18 min read
Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench

Qwen3-Coder-Next: 80B total, 3B active, 70.6 on SWE-Bench

Comments
4 min read
# The Missing Layer of the AI Agent Stack: A Machine-to-Machine Search Engine

# The Missing Layer of the AI Agent Stack: A Machine-to-Machine Search Engine

Comments
3 min read
Building a Serverless AI Model Evaluation Platform on AWS

Building a Serverless AI Model Evaluation Platform on AWS

1
Comments 2
6 min read
How to Scale AI Development Beyond Prototype Speed

How to Scale AI Development Beyond Prototype Speed

1
Comments
10 min read
Gemini 3.5 Flash Developer Guide

Gemini 3.5 Flash Developer Guide

68
Comments 7
8 min read
What’s the best tech stack for AI app development?

What’s the best tech stack for AI app development?

1
Comments
8 min read
Run Hermes Agent on Any Model — Free, Local, and Cost-Routed

Run Hermes Agent on Any Model — Free, Local, and Cost-Routed

Comments
6 min read
How to Run a 35B Parameter Model on Your Laptop Without Melting It

How to Run a 35B Parameter Model on Your Laptop Without Melting It

Comments
5 min read
RAG: How AI Models Use Your Data Without Forgetting

RAG: How AI Models Use Your Data Without Forgetting

4
Comments 2
14 min read
How My Career Evolved Like an AI (LLM Architectures)System

How My Career Evolved Like an AI (LLM Architectures)System

Comments
5 min read
We built traceAI, an open-source tool for tracing LLM calls in production

We built traceAI, an open-source tool for tracing LLM calls in production

Comments
1 min read
ZAYA1-8B: a 760M-active MoE trained on AMD MI300x

ZAYA1-8B: a 760M-active MoE trained on AMD MI300x

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