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.
GLM-5.3 Sometimes Reasons About How Its Outputs Shape Future Training

GLM-5.3 Sometimes Reasons About How Its Outputs Shape Future Training

Comments
3 min read
Introduction to Machine Learning: A Practical Beginner Guide for Beginners

Introduction to Machine Learning: A Practical Beginner Guide for Beginners

1
Comments
4 min read
safe_mode=True does nothing for a .h5 Keras model: a static check for CVE-2025-9905

safe_mode=True does nothing for a .h5 Keras model: a static check for CVE-2025-9905

Comments
3 min read
Your AI Is Accurate. But Is It Fair, Ethical, or Even Trustworthy?

Your AI Is Accurate. But Is It Fair, Ethical, or Even Trustworthy?

1
Comments
12 min read
Edit the Weights, Retrieve the Fact, or Look It Up in a Graph?

Edit the Weights, Retrieve the Fact, or Look It Up in a Graph?

Comments 1
2 min read
NVIDIA GTC Berlin 2026: Jensen Huang's Oct 21 Keynote Preview

NVIDIA GTC Berlin 2026: Jensen Huang's Oct 21 Keynote Preview

Comments
2 min read
40 GB to 6.7 GB: The 3-Bit Trick That Shrinks Your KV Cache 6x

40 GB to 6.7 GB: The 3-Bit Trick That Shrinks Your KV Cache 6x

1
Comments 1
5 min read
FP16 Quantization Quality Loss: We Blamed the Architecture, the Bug Was One Overflowed Tensor

FP16 Quantization Quality Loss: We Blamed the Architecture, the Bug Was One Overflowed Tensor

Comments
10 min read
Self-Hosting Open-Weight LLMs in the EU: A GDPR Checklist

Self-Hosting Open-Weight LLMs in the EU: A GDPR Checklist

Comments
6 min read
AirSketch

AirSketch

5
Comments
6 min read
The layer every model-file scanner skips: catching nested-archive evasion statically

The layer every model-file scanner skips: catching nested-archive evasion statically

Comments
3 min read
How an LLM actually makes one word

How an LLM actually makes one word

Comments
3 min read
DeepSeek V4.1-Flash-1017: Cheaper AI Agents, Bigger Claims — What We Can Actually Verify

DeepSeek V4.1-Flash-1017: Cheaper AI Agents, Bigger Claims — What We Can Actually Verify

Comments
2 min read
The Geometry of Shadows: What a Bridge Railing Taught Me About the Mathematics of LLMs

The Geometry of Shadows: What a Bridge Railing Taught Me About the Mathematics of LLMs

Comments
4 min read
Accelerator certification speeds VLA models 10

Accelerator certification speeds VLA models 10

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