DEV Community

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Why Your Inference Stack Is Bleeding Money — And How to Fix It

Why Your Inference Stack Is Bleeding Money — And How to Fix It

Comments
6 min read
What happens when you hide embeddings but keep search working?

What happens when you hide embeddings but keep search working?

1
Comments
3 min read
Claude Code v2.1.117 Boosts Opus 4.7; Anthropic Org Ban Alert; DIY LLM Build Experience

Claude Code v2.1.117 Boosts Opus 4.7; Anthropic Org Ban Alert; DIY LLM Build Experience

Comments
3 min read
I'm a Master's Student in AI & Big Data. And AI Just Gave Me My Freedom Back.

I'm a Master's Student in AI & Big Data. And AI Just Gave Me My Freedom Back.

3
Comments 2
4 min read
RAG Systems in Production: Building Enterprise Knowledge Search

RAG Systems in Production: Building Enterprise Knowledge Search

Comments
22 min read
Chapter 3: The Tokenizer - Text to Numbers and Back

Chapter 3: The Tokenizer - Text to Numbers and Back

Comments
2 min read
AI 週報:2026/04/17–04/24 OpenAI 一週連發、Anthropic 撞翻 Figma、Mythos 進入政治場

AI 週報:2026/04/17–04/24 OpenAI 一週連發、Anthropic 撞翻 Figma、Mythos 進入政治場

Comments 1
4 min read
Your LLM-as-judge eval set is too small. Here is the math

Your LLM-as-judge eval set is too small. Here is the math

7
Comments 1
4 min read
How FinOps Supports Responsible and Sustainable AI Development

How FinOps Supports Responsible and Sustainable AI Development

Comments
2 min read
Redes Neuronales Convolucionales - Clasificacione de imagenes Landmarks

Redes Neuronales Convolucionales - Clasificacione de imagenes Landmarks

Comments
1 min read
The $1 Trillion Problem: How We're Building AI Agents for the Industry That Hates Software

The $1 Trillion Problem: How We're Building AI Agents for the Industry That Hates Software

8
Comments
3 min read
I Tested Three AI Memory Retrieval Strategies. The Hard Failure Was Semantic

I Tested Three AI Memory Retrieval Strategies. The Hard Failure Was Semantic

Comments
8 min read
Promptfoo is a CI gate, not an eval framework. Treating it like one cost us $4,200

Promptfoo is a CI gate, not an eval framework. Treating it like one cost us $4,200

Comments 1
4 min read
DARKNET-53

DARKNET-53

Comments
2 min read
Beyond the "Brute Force Beauty": A Modular, Brain-Inspired LLM Architecture (Thoughts on grand models: Part 2)

Beyond the "Brute Force Beauty": A Modular, Brain-Inspired LLM Architecture (Thoughts on grand models: Part 2)

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