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.
Your Feedback Made This Better — Here's What Changed

Your Feedback Made This Better — Here's What Changed

2
Comments 6
7 min read
AI/ML Research Digest — Jun 06, 2026

AI/ML Research Digest — Jun 06, 2026

1
Comments
3 min read
How to Get 2x Speed on Gemma 4 with Multi-Token Prediction in llama.cpp

How to Get 2x Speed on Gemma 4 with Multi-Token Prediction in llama.cpp

Comments
3 min read
Fine-Tuning and RAG: What a Dozen Failed Experiments Taught Me

Fine-Tuning and RAG: What a Dozen Failed Experiments Taught Me

1
Comments
7 min read
Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB VRAM

Gemma 4 QAT on 10GB Laptop: Local AI with 6.7GB VRAM

Comments
1 min read
Manticore Search 28.4.4: Faster KNN, better conversational search, easier installs and more faceting controls

Manticore Search 28.4.4: Faster KNN, better conversational search, easier installs and more faceting controls

Comments 1
5 min read
I built a feature store in pure Python to finally understand the point-in-time join

I built a feature store in pure Python to finally understand the point-in-time join

Comments
6 min read
The Prefill Wall: Why MTP's 2 Barely Moves Long-Context Latency (Qwen3.6-27B, RTX 3090)

The Prefill Wall: Why MTP's 2 Barely Moves Long-Context Latency (Qwen3.6-27B, RTX 3090)

Comments
4 min read
🤖 I Built a Semantic FAQ Bot That Understands Meaning Instead of Keywords | Project #4

🤖 I Built a Semantic FAQ Bot That Understands Meaning Instead of Keywords | Project #4

Comments
3 min read
AlbumentationsX MCP

AlbumentationsX MCP

1
Comments 1
1 min read
I was fine-tuning a language model on a new language. The loss was perfect. It spoke Chinese.

I was fine-tuning a language model on a new language. The loss was perfect. It spoke Chinese.

Comments
3 min read
Building an AI Claims-Adjuster Agent: Architecture, Guardrails, and the Data It Actually Needs

Building an AI Claims-Adjuster Agent: Architecture, Guardrails, and the Data It Actually Needs

Comments
4 min read
Context Compaction Visualizer: See Exactly What Your AI Agent Forgot Before It Costs You

Context Compaction Visualizer: See Exactly What Your AI Agent Forgot Before It Costs You

8
Comments 4
7 min read
Neura has Amazon, Nvidia and Europe's Sovereign Capital in its Corner. The Humanoid Race just got geopolitical.

Neura has Amazon, Nvidia and Europe's Sovereign Capital in its Corner. The Humanoid Race just got geopolitical.

Comments
8 min read
Two architectures for "script to video", and why the credit meter follows from the design

Two architectures for "script to video", and why the credit meter follows from the design

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