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.
GPT Image 2.6 vs 2.5 vs 2.0: Character Consistency and Real Results

GPT Image 2.6 vs 2.5 vs 2.0: Character Consistency and Real Results

Comments
10 min read
Quantcheck flags unsafe low‑bit LLMs

Quantcheck flags unsafe low‑bit LLMs

Comments
2 min read
Document Classification With Python and LLMs

Document Classification With Python and LLMs

Comments
8 min read
SWE-bench Verified on Hugging Face: 9 Self-Reported Rows Top the Official Table's Best, and 6 Repos Fill 16 of 78 Rows

SWE-bench Verified on Hugging Face: 9 Self-Reported Rows Top the Official Table's Best, and 6 Repos Fill 16 of 78 Rows

Comments 1
14 min read
Human-in-the-loop architecture

Human-in-the-loop architecture

Comments
5 min read
Ripple-65B Is an Open Coder With 1M Context. Its DGX Spark Script Stops at 128K

Ripple-65B Is an Open Coder With 1M Context. Its DGX Spark Script Stops at 128K

Comments
8 min read
Beyond the Grid: The Frontier of Geometric Deep Learning

Beyond the Grid: The Frontier of Geometric Deep Learning

Comments
3 min read
Watermarking vs AI Detection: SynthID, C2PA and Classifiers Compared

Watermarking vs AI Detection: SynthID, C2PA and Classifiers Compared

Comments
4 min read
My Gradient Clipping Was Never Clipping. It Was Secretly Multiplying My Weight Decay

My Gradient Clipping Was Never Clipping. It Was Secretly Multiplying My Weight Decay

Comments
4 min read
Warmup Did Nothing for My Learning Rate — Then It Fully Rescued the Wrong One

Warmup Did Nothing for My Learning Rate — Then It Fully Rescued the Wrong One

Comments
4 min read
SWE-2 Flash: Cognition's 3x-Faster, 5x-Cheaper Coding Model, Explained

SWE-2 Flash: Cognition's 3x-Faster, 5x-Cheaper Coding Model, Explained

Comments
2 min read
B300 vs B200: what does Blackwell Ultra add for training?

B300 vs B200: what does Blackwell Ultra add for training?

Comments
8 min read
"Trace Shape Reveals Model Capability: 3B vs 7B"

"Trace Shape Reveals Model Capability: 3B vs 7B"

1
Comments 3
2 min read
Postman, Claude Code, and the Plugin You Never Installed

Postman, Claude Code, and the Plugin You Never Installed

Comments
6 min read
Turing Award Winner(David Patterson): The Difference Between a CPU, GPU, and TPU | GPU 和 TPU 的本质区别

Turing Award Winner(David Patterson): The Difference Between a CPU, GPU, and TPU | GPU 和 TPU 的本质区别

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