DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
🧩 Runtime Snapshots #5 — The Real Thing: How We Actually Use It

🧩 Runtime Snapshots #5 — The Real Thing: How We Actually Use It

1
Comments
2 min read
Large File MCP: Handle Massive Files in Claude with Intelligent Chunking

Large File MCP: Handle Massive Files in Claude with Intelligent Chunking

Comments
5 min read
Nov14, 2025 | The Tongyi Weekly: Your weekly dose of cutting-edge AI from Tongyi Lab

Nov14, 2025 | The Tongyi Weekly: Your weekly dose of cutting-edge AI from Tongyi Lab

Comments
5 min read
Speculative Decoding: Making LLMs Faster Without Sacrificing Quality

Speculative Decoding: Making LLMs Faster Without Sacrificing Quality

1
Comments
14 min read
The Security Logic Behind LLM Jailbreaking

The Security Logic Behind LLM Jailbreaking

1
Comments
6 min read
LangGraph: Orchestrating Complex LLM Workflows with State Machines

LangGraph: Orchestrating Complex LLM Workflows with State Machines

Comments
4 min read
LLMs Are Dying - The New AI Is Killing Them

LLMs Are Dying - The New AI Is Killing Them

1
Comments
10 min read
Understanding AI: From LLMs to MCP

Understanding AI: From LLMs to MCP

Comments
8 min read
The Best LLM and AI Orchestration Toolkits for Your Stack

The Best LLM and AI Orchestration Toolkits for Your Stack

Comments
4 min read
From SEO Playbooks to GEO Architectures

From SEO Playbooks to GEO Architectures

3
Comments
13 min read
I might have gone overboard. I built a custom LLM for my .env extension... and now I just shipped a massive UI overhaul for it.

I might have gone overboard. I built a custom LLM for my .env extension... and now I just shipped a massive UI overhaul for it.

5
Comments
2 min read
🧩 LangGraph 𓅃 : Building Smarter AI 🤖 Workflows with Graphs Instead of Chains

🧩 LangGraph 𓅃 : Building Smarter AI 🤖 Workflows with Graphs Instead of Chains

Comments
4 min read
Adding NVIDIA GPU Support to Docker Model Runner

Adding NVIDIA GPU Support to Docker Model Runner

Comments
6 min read
Fine-Tuning LLMs: LoRA, Quantization, and Distillation Simplified

Fine-Tuning LLMs: LoRA, Quantization, and Distillation Simplified

1
Comments
5 min read
How I Automated the Transcription of 91 Instagram (screenshots) Poems Using Python + LLM Vision (Real Case Study)

How I Automated the Transcription of 91 Instagram (screenshots) Poems Using Python + LLM Vision (Real Case Study)

13
Comments
3 min read
Creating Custom Evaluators to Measure Model Quality

Creating Custom Evaluators to Measure Model Quality

Comments
9 min read
Running Out of Data: How Synthetic Data is Saving the Future of AI

Running Out of Data: How Synthetic Data is Saving the Future of AI

10
Comments
4 min read
Notes on the margins

Notes on the margins

Comments
3 min read
How to Ensure Quality of Responses in AI Agents

How to Ensure Quality of Responses in AI Agents

Comments
13 min read
Preventing AI Project Failures Through Effective Prompt Engineering

Preventing AI Project Failures Through Effective Prompt Engineering

1
Comments
5 min read
Building Your First Sentiment Analysis App with LangChain LCEL and OpenAI

Building Your First Sentiment Analysis App with LangChain LCEL and OpenAI

2
Comments
9 min read
Model Collapse: The AI Feedback Loop Problem Nobody Wants to Talk About

Model Collapse: The AI Feedback Loop Problem Nobody Wants to Talk About

Comments
5 min read
Understanding the Role of a Context Engineer

Understanding the Role of a Context Engineer

Comments
19 min read
2025 Complete Guide: In-Depth Analysis of ERNIE-4.5-VL-28B-A3B-Thinking Multimodal AI Model

2025 Complete Guide: In-Depth Analysis of ERNIE-4.5-VL-28B-A3B-Thinking Multimodal AI Model

Comments
12 min read
I Let an LLM Write JavaScript Inside My AI Runtime. Here’s What Happened

I Let an LLM Write JavaScript Inside My AI Runtime. Here’s What Happened

5
Comments 1
5 min read
loading...