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.
The 128-Vector Trick: Why Perplexity Stopped Squeezing Documents Into One Vector

The 128-Vector Trick: Why Perplexity Stopped Squeezing Documents Into One Vector

Comments 1
6 min read
Neural Networks, its Inspiration and Various Components.

Neural Networks, its Inspiration and Various Components.

Comments
4 min read
Learn Holdout Leakage by Building a Tiny Split Receipt

Learn Holdout Leakage by Building a Tiny Split Receipt

Comments
9 min read
JEV-27B: How AutoTrust AI Built an Open Decision Model That Thinks Fast and Reasons Deep

JEV-27B: How AutoTrust AI Built an Open Decision Model That Thinks Fast and Reasons Deep

Comments
5 min read
Is a 10x Jump Always a 10x Jump? A Statistical Audit of the METR Time-Horizon Plot

Is a 10x Jump Always a 10x Jump? A Statistical Audit of the METR Time-Horizon Plot

Comments
5 min read
Liquid AI's d1 Decision Models Went Open: Triage Support Tickets on a CPU With the 600M One (and Where It Fools You)

Liquid AI's d1 Decision Models Went Open: Triage Support Tickets on a CPU With the 600M One (and Where It Fools You)

Comments
6 min read
The sim writes the story — an unedited 11-minute session of a milsim RTT

The sim writes the story — an unedited 11-minute session of a milsim RTT

Comments
2 min read
Meet Jev: The Fast, Cheap AI That Only Picks, Never Writes

Meet Jev: The Fast, Cheap AI That Only Picks, Never Writes

Comments
10 min read
Computer Vision for Beginners: From Pixels to Predictions

Computer Vision for Beginners: From Pixels to Predictions

1
Comments 1
7 min read
Reading the S1MB result: why Borda aggregation makes a #1 harder to fake

Reading the S1MB result: why Borda aggregation makes a #1 harder to fake

Comments
2 min read
On a Tesla P40, loading a diffusion model in fp16 made it 14x slower than fp32

On a Tesla P40, loading a diffusion model in fp16 made it 14x slower than fp32

Comments
2 min read
Learn TensorRT: a C++17 path from YOLOv8 to async inference

Learn TensorRT: a C++17 path from YOLOv8 to async inference

Comments 1
1 min read
EmbeddingGemma 2: How Google's Open Multimodal Embedding Model Works

EmbeddingGemma 2: How Google's Open Multimodal Embedding Model Works

Comments
5 min read
How to Build an Internal LLM Benchmark for Enterprise Model Selection

How to Build an Internal LLM Benchmark for Enterprise Model Selection

Comments
8 min read
Your agent's hardest call is the one you can't test

Your agent's hardest call is the one you can't test

Comments 1
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.