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.
How to build a reliable video-to-prompt pipeline
videoflow profile

How to build a reliable video-to-prompt pipeline

#ai #tutorial #machinelearning #architecture
Comments 1
5 min read
A Cognitive Benchmark for Code-RAG Retrieval: Part 2 — Why Model Rankings Depend on the Pipeline
miftakhov profile

A Cognitive Benchmark for Code-RAG Retrieval: Part 2 — Why Model Rankings Depend on the Pipeline

#rag #ai #java #machinelearning
Comments
15 min read
Porting a 128-expert MoE (Gemma-4 26B-A4B) to AWS Inferentia2 — where every rank weighted the wrong experts
xbill profile

Porting a 128-expert MoE (Gemma-4 26B-A4B) to AWS Inferentia2 — where every rank weighted the wrong experts

#machinelearning #aws #ai #python
2
Comments
6 min read
Let's welcome NOVA
hrithish_raj_d3d46f974a26 profile

Let's welcome NOVA

#gonova #api #machinelearning #devops
Comments
1 min read
My Inferentia port matched its reference token-for-token — and still output garbage
xbill profile

My Inferentia port matched its reference token-for-token — and still output garbage

#machinelearning #aws #ai #python
1
Comments
8 min read
LifeLine Loop — AI-Powered Food Rescue Platform
suhanayadav4 profile

LifeLine Loop — AI-Powered Food Rescue Platform

#showdev #ai #machinelearning #startup
Comments
3 min read
Build a Private AI App Platform with Dify and Ollama
everylocalai profile

Build a Private AI App Platform with Dify and Ollama

#ai #webdev #machinelearning #beginners
Comments
2 min read
Hillock: A brain-inspired, CPU-bound memory gate for local LLMs
roandejager profile

Hillock: A brain-inspired, CPU-bound memory gate for local LLMs

#ai #python #opensource #machinelearning
1
Comments
2 min read
Does Quantization Break Tool-Calling? I Measured It on a 4GB Laptop GPU (BFCL, 3 Seeds, Bootstrap 95% CI)

Model family outperforms size as a predictor
happynood profile
Alexey

Does Quantization Break Tool-Calling? I Measured It on a 4GB Laptop GPU (BFCL, 3 Seeds, Bootstrap 95% CI)

#llm #machinelearning #python #opensource
3
Comments 10
4 min read
How Developers Really Use AI: Claude, Codex, and the Skills Debate
lanternproton profile

How Developers Really Use AI: Claude, Codex, and the Skills Debate

#ai #machinelearning #devtools #programming
1
Comments
1 min read
Documents Aren't Bags of Chunks
valerykot profile

Documents Aren't Bags of Chunks

#ai #rag #programming #machinelearning
15
Comments 35
3 min read
Optimal Transport Converts Dense Layers to Sparse Experts
olaughter profile

Optimal Transport Converts Dense Layers to Sparse Experts

#ai #machinelearning #abotwrotethis
Comments
2 min read
Vector Databases Are Not Magic, Here's What's Actually Happening Under the Hood
shayan_holakouee profile

Vector Databases Are Not Magic, Here's What's Actually Happening Under the Hood

#ai #vectordatabase #python #machinelearning
Comments
9 min read
AI Agents in Production: Structured Generation for AI Workflows
shaktiwadekar profile

AI Agents in Production: Structured Generation for AI Workflows

#ai #machinelearning #architecture #agents
Comments
6 min read
Building a RAG pipeline in a weekend
akshay_sarak profile

Building a RAG pipeline in a weekend

#ai #machinelearning #webdev #systemdesign
1
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.