DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Endo.AI - Multimodal Endocrinology Assistant with Google Gemini

Endo.AI - Multimodal Endocrinology Assistant with Google Gemini

Comments
4 min read
From 260 Lines to 5: How We Built a Zero-Maintenance LLM Integration SDK

From 260 Lines to 5: How We Built a Zero-Maintenance LLM Integration SDK

Comments
4 min read
TL;DR — We’re Using AI to Write Code Because We’re Lazy, and Not Putting AI in Software Because That’s Hard

TL;DR — We’re Using AI to Write Code Because We’re Lazy, and Not Putting AI in Software Because That’s Hard

5
Comments
2 min read
Open Source AI

Open Source AI

Comments
11 min read
🚀 Meet the first Small Language Model built for DevOps 🚀

🚀 Meet the first Small Language Model built for DevOps 🚀

Comments
2 min read
Quantization Explained: A Concise Guide for LLMs

Quantization Explained: A Concise Guide for LLMs

Comments
3 min read
Stop Writing Your Own Validators

Stop Writing Your Own Validators

3
Comments 1
2 min read
Why JSON Mode Fails (and How to Fix It)

Why JSON Mode Fails (and How to Fix It)

Comments
2 min read
I Used Autogen GraphFlow and Qwen3 Coder to Solve Math Problems — And It Worked

I Used Autogen GraphFlow and Qwen3 Coder to Solve Math Problems — And It Worked

1
Comments
12 min read
The Developer’s Roadmap to Building and Deploying AI Models

The Developer’s Roadmap to Building and Deploying AI Models

Comments
3 min read
Beyond the Buzzwords: How Generative AI Really Works

Beyond the Buzzwords: How Generative AI Really Works

1
Comments
12 min read
All Data and AI Weekly #206: 08 Sept 2025

All Data and AI Weekly #206: 08 Sept 2025

5
Comments
5 min read
How to Install & Run Microsoft Kosmos-2.5 Locally?

How to Install & Run Microsoft Kosmos-2.5 Locally?

5
Comments
13 min read
We built memory for AI apps focusing on individuals and achieved SOTA (88.24%) on LoCoMo benchmark

We built memory for AI apps focusing on individuals and achieved SOTA (88.24%) on LoCoMo benchmark

2
Comments
2 min read
AI Solves the Unsolvable: Automating Optimization with LLMs by Arvind Sundararajan

AI Solves the Unsolvable: Automating Optimization with LLMs by Arvind Sundararajan

5
Comments
2 min read
Build, Run, Chat: Creating a Self-Hosted LLM Setup

Build, Run, Chat: Creating a Self-Hosted LLM Setup

9
Comments
4 min read
Tracking AI system performance using AI Evaluation Reports

Tracking AI system performance using AI Evaluation Reports

3
Comments 1
10 min read
Anthropic Just Paid $1.5B for Using Pirated Books to Train Claude - Here's What This Means for Developers

Anthropic Just Paid $1.5B for Using Pirated Books to Train Claude - Here's What This Means for Developers

10
Comments
4 min read
Why Success Favors Action and How This Relates to AI

Why Success Favors Action and How This Relates to AI

5
Comments
2 min read
RAG Firewall: The missing retrieval-time security layer for LLMs (v0.4.1)

RAG Firewall: The missing retrieval-time security layer for LLMs (v0.4.1)

Comments
2 min read
Building a Local Documentation Chatbot with Python, FAISS, and OpenAI

Building a Local Documentation Chatbot with Python, FAISS, and OpenAI

2
Comments
7 min read
The Ultimate Showdown: Grok Code Fast 1 vs Claude Sonnet 4 - Which AI Coding Assistant Will Win Your Heart (and Wallet)?

The Ultimate Showdown: Grok Code Fast 1 vs Claude Sonnet 4 - Which AI Coding Assistant Will Win Your Heart (and Wallet)?

1
Comments
6 min read
Early Feedback on “Build a Reasoning Model (From Scratch)”

Early Feedback on “Build a Reasoning Model (From Scratch)”

5
Comments
3 min read
How We Are Misusing LLMs

How We Are Misusing LLMs

1
Comments
3 min read
My Take on Vibe Code

My Take on Vibe Code

Comments
2 min read
loading...