DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Hướng Dẫn Tự Tạo Mã Claude

Hướng Dẫn Tự Tạo Mã Claude

Comments
15 min read
LiteLLM vs AegisFlow: honest comparison from someone who built the alternative

LiteLLM vs AegisFlow: honest comparison from someone who built the alternative

Comments
3 min read
Why AI Agent Outputs Need Adversarial Review (and How to Add It in One API Call)

Why AI Agent Outputs Need Adversarial Review (and How to Add It in One API Call)

Comments
4 min read
LLM Code Reviews on pre-commit : A Solo Dev’s New Best Friend?

LLM Code Reviews on pre-commit : A Solo Dev’s New Best Friend?

1
Comments 1
2 min read
Reducing bootstrap memory cost in LLM agents

Reducing bootstrap memory cost in LLM agents

Comments
1 min read
TurboQuant MoE 0.3.0

TurboQuant MoE 0.3.0

Comments
1 min read
Open sourced my Claude Code + NVIDIA NIM stack — run Claude Code with free models

Open sourced my Claude Code + NVIDIA NIM stack — run Claude Code with free models

Comments
1 min read
ContextCraft: A Visual Workbench for Building and Managing LLM Context Windows

ContextCraft: A Visual Workbench for Building and Managing LLM Context Windows

4
Comments
6 min read
ClawHavoc and the Missing Layer: Why Scanning Agent Skills Isn't Enough

ClawHavoc and the Missing Layer: Why Scanning Agent Skills Isn't Enough

Comments
3 min read
Why We Built AgentsBay

Why We Built AgentsBay

Comments
3 min read
🔥 Fine-Tuning Gemma 4 on Your Own Dataset: A Step-by-Step Guide

🔥 Fine-Tuning Gemma 4 on Your Own Dataset: A Step-by-Step Guide

1
Comments
60 min read
How AgentsBay Negotiation Works: A State Machine for Agent Commerce

How AgentsBay Negotiation Works: A State Machine for Agent Commerce

Comments
4 min read
Understanding Decoder-Only Transformers Part 1: Masked Self-Attention

Understanding Decoder-Only Transformers Part 1: Masked Self-Attention

16
Comments
1 min read
From OOM to 262K Context: Running Qwen3-Coder 30B Locally on 8GB VRAM

From OOM to 262K Context: Running Qwen3-Coder 30B Locally on 8GB VRAM

4
Comments 1
8 min read
Building a RAG Evaluation Harness That Actually Catches Problems

Building a RAG Evaluation Harness That Actually Catches Problems

3
Comments 1
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.