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.
Liquid Neural Networks: The AI That Adapts on the Fly

Liquid Neural Networks: The AI That Adapts on the Fly

Comments
1 min read
What GPU do you need for Qwen3.8, Qwen3.6, Gemma 4 and gpt-oss locally? (measured, Oct 2026)

What GPU do you need for Qwen3.8, Qwen3.6, Gemma 4 and gpt-oss locally? (measured, Oct 2026)

1
Comments 5
8 min read
How an AI Agent Taught NVIDIA's $399 Robot Duck to Walk: Prompt to Policy in 7 Steps

How an AI Agent Taught NVIDIA's $399 Robot Duck to Walk: Prompt to Policy in 7 Steps

Comments
3 min read
Turning an old photo into a moving clip: the model side nobody explains

Turning an old photo into a moving clip: the model side nobody explains

Comments
3 min read
The Judgment Layer: How AI Learned to Grade What It Can't Verify

The Judgment Layer: How AI Learned to Grade What It Can't Verify

Comments
4 min read
Best AI Voice Generators in 2026: 7 Tools Compared for Creators and Builders

Best AI Voice Generators in 2026: 7 Tools Compared for Creators and Builders

Comments
3 min read
TensorRT INT8 vs FP16 on RF-DETR, Measured on an RTX 5090

TensorRT INT8 vs FP16 on RF-DETR, Measured on an RTX 5090

Comments
9 min read
ScaleDown CDMs: Fast, Cheap Classify, Extract and Summarize Models Tested

ScaleDown CDMs: Fast, Cheap Classify, Extract and Summarize Models Tested

Comments
8 min read
MOSS-Image Publishes 5B DiT Weights and Layout JSON Workflow

MOSS-Image Publishes 5B DiT Weights and Layout JSON Workflow

Comments
3 min read
I measured softmax's precision cliff. In fp32, cross-entropy returns exactly zero at margin 16.

I measured softmax's precision cliff. In fp32, cross-entropy returns exactly zero at margin 16.

Comments
7 min read
OLMo-3 Checkpoints Question Whether RLVR Drives Instrumental Convergence

OLMo-3 Checkpoints Question Whether RLVR Drives Instrumental Convergence

Comments
1 min read
IAB Content Taxonomy 3.1 and GARM in 2026: three facts AI answers get wrong

IAB Content Taxonomy 3.1 and GARM in 2026: three facts AI answers get wrong

Comments
3 min read
Building an AI That Knows When Not to Guess

Building an AI That Knows When Not to Guess

Comments
6 min read
40 āļ§āļīāļ™āļēāļ—āļĩāļˆāļēāļ y = wx + b āļ–āļķāļ‡ ChatGPT: āļ„āļ“āļīāļ•āļĻāļēāļŠāļ•āļĢāđŒāđ€āļŠāđ‰āļ™āđ€āļ”āļĩāļĒāļ§āļ—āļĩāđˆāļ­āļ˜āļīāļšāļēāļĒ AI āđ„āļ”āđ‰āļ—āļąāđ‰āļ‡āļŦāļĄāļ”?

40 āļ§āļīāļ™āļēāļ—āļĩāļˆāļēāļ y = wx + b āļ–āļķāļ‡ ChatGPT: āļ„āļ“āļīāļ•āļĻāļēāļŠāļ•āļĢāđŒāđ€āļŠāđ‰āļ™āđ€āļ”āļĩāļĒāļ§āļ—āļĩāđˆāļ­āļ˜āļīāļšāļēāļĒ AI āđ„āļ”āđ‰āļ—āļąāđ‰āļ‡āļŦāļĄāļ”?

Comments
2 min read
When an AI Agent Resumes, How Do You Prevent a Tool from Running Twice?

When an AI Agent Resumes, How Do You Prevent a Tool from Running Twice?

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