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.
Can You Steer It? Introducing SEWO — A Steerable Medicine World Model Framework

Can You Steer It? Introducing SEWO — A Steerable Medicine World Model Framework

1
Comments
3 min read
Stop LLM Hallucinations: Best-of-N vs. Consensus Mechanisms

Stop LLM Hallucinations: Best-of-N vs. Consensus Mechanisms

5
Comments
3 min read
Psychology x AI: 23 Cognitive Science Techniques That Improve LLM Output by 15-40%

Psychology x AI: 23 Cognitive Science Techniques That Improve LLM Output by 15-40%

Comments
9 min read
Anthropic Preps Opus 4.7, Claude Code Gains Routines & Autoresearch Plugin

Anthropic Preps Opus 4.7, Claude Code Gains Routines & Autoresearch Plugin

Comments
3 min read
How AI-Generated Content Is Making Scam Detection Harder Than Ever

How AI-Generated Content Is Making Scam Detection Harder Than Ever

Comments
8 min read
SmolVLM2 Edge Vision Agent: Visual Monitoring Without a GPU or Cloud API

SmolVLM2 Edge Vision Agent: Visual Monitoring Without a GPU or Cloud API

2
Comments
7 min read
I Increased Retrieval From Top-5 to Top-20. My Answers Got Worse

I Increased Retrieval From Top-5 to Top-20. My Answers Got Worse

1
Comments 1
6 min read
From Smart Chips to AI Teaching Grants—EU Act Risk, MCU Compression, and Brain Tumor Equity

From Smart Chips to AI Teaching Grants—EU Act Risk, MCU Compression, and Brain Tumor Equity

Comments
2 min read
Teaching an AI System to Remember What It Learned: Building a Conflict Mediator with Persistent Agent Memory

Teaching an AI System to Remember What It Learned: Building a Conflict Mediator with Persistent Agent Memory

Comments
6 min read
Searching Billions in Seconds: How HNSW Solved the Scale Problem

Searching Billions in Seconds: How HNSW Solved the Scale Problem

10
Comments
6 min read
38% of AI Answers Are Wrong — And It's Your Prompt's Fault

38% of AI Answers Are Wrong — And It's Your Prompt's Fault

Comments
3 min read
EVAL #010: The AI Coding Agent Wars — 10 Agents, 4 Architectures, 1 Winner (For Now)

EVAL #010: The AI Coding Agent Wars — 10 Agents, 4 Architectures, 1 Winner (For Now)

Comments
12 min read
Building NEXUS: How I Architected a Multi-Agent AI System on Google Cloud in 48 Hours

Building NEXUS: How I Architected a Multi-Agent AI System on Google Cloud in 48 Hours

1
Comments 2
3 min read
Why long-running agents start repeating themselves after a few hours

Why long-running agents start repeating themselves after a few hours

Comments
1 min read
On-Device ML iOS: Why Apple's Foundation Models Change Everything

On-Device ML iOS: Why Apple's Foundation Models Change Everything

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