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

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Hark's AI assistant runs locally as an operating system layer, not an app

Hark's AI assistant runs locally as an operating system layer, not an app

Comments
2 min read
Product Matching Is Mostly About Avoiding Confident Wrong Answers

Product Matching Is Mostly About Avoiding Confident Wrong Answers

Comments
5 min read
Reka's Rho-1: What Happens When One Model Replaces Your Multimodal Pipeline

Reka's Rho-1: What Happens When One Model Replaces Your Multimodal Pipeline

Comments
4 min read
Is Tesseract accurate enough for production?

Is Tesseract accurate enough for production?

Comments
5 min read
Dust: The Radical Idea of Training AI Without Backpropagation

Dust: The Radical Idea of Training AI Without Backpropagation

Comments
4 min read
Understanding Prism: Dynamic Sparse Attention for Joint Video-Audio Generation

Understanding Prism: Dynamic Sparse Attention for Joint Video-Audio Generation

Comments
4 min read
When a 0.4-Point Lead Means Nothing: Reading Open-Model Leaderboard Margins Like a Statistician

When a 0.4-Point Lead Means Nothing: Reading Open-Model Leaderboard Margins Like a Statistician

Comments
7 min read
Engenharia de IA - Estudo sobre como modelos de linguagem funcionam

Engenharia de IA - Estudo sobre como modelos de linguagem funcionam

Comments
1 min read
A Book Recommender That Nails Harry Potter and Fumbles Seven Plays

A Book Recommender That Nails Harry Potter and Fumbles Seven Plays

Comments
2 min read
How Logistic Regression Works: Beginner to Pro Guide

How Logistic Regression Works: Beginner to Pro Guide

Comments
6 min read
Reflection AI's Beam: Why 23B Active Parameters Matter More Than 501B

Reflection AI's Beam: Why 23B Active Parameters Matter More Than 501B

Comments
3 min read
The great sparsification: 2026 open-weight MoE models now activate 1 to 9 percent of their weights

The great sparsification: 2026 open-weight MoE models now activate 1 to 9 percent of their weights

Comments
6 min read
The Wiki Write That Wasn't a Write: Why Agent Guardrails Must Check Outcomes, Not Tools

The Wiki Write That Wasn't a Write: Why Agent Guardrails Must Check Outcomes, Not Tools

Comments 1
6 min read
AI Photo Realism: Why Phone Snapshots Beat Studio Shots

AI Photo Realism: Why Phone Snapshots Beat Studio Shots

Comments
7 min read
We removed 98.77% of an LLM’s input. Accuracy went up.

We removed 98.77% of an LLM’s input. Accuracy went up.

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