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.
How I optimized Andrej Karpathy's "autoresearch" for 2GB GPUs

How I optimized Andrej Karpathy's "autoresearch" for 2GB GPUs

1
Comments
2 min read
From Pixels to Physicality ☃️: Engineering Olaf with Reinforcement ✨ Learning, Control Systems, and Illusion Design 🤖

From Pixels to Physicality ☃️: Engineering Olaf with Reinforcement ✨ Learning, Control Systems, and Illusion Design 🤖

2
Comments
8 min read
Surviving 12GB VRAM : Autonomous Memory Management for Local QLoRA Fine Tuning

Surviving 12GB VRAM : Autonomous Memory Management for Local QLoRA Fine Tuning

1
Comments
3 min read
Drift Artifact: A Method for Writing That Performs Its Own Argument

Drift Artifact: A Method for Writing That Performs Its Own Argument

1
Comments
3 min read
Speaker Diarization: How AI Knows Who Said What

Speaker Diarization: How AI Knows Who Said What

Comments
5 min read
They Built Your World. Now They're Being Told They're Obsolete.

They Built Your World. Now They're Being Told They're Obsolete.

Comments
6 min read
Why Asking an LLM for JSON Isn’t Enough

Why Asking an LLM for JSON Isn’t Enough

24
Comments 38
4 min read
I Built an Open-Source Immune System for LLMs That Detects Jailbreaks in 3ms — Here's What I Found Auditing Lakera Guard

I Built an Open-Source Immune System for LLMs That Detects Jailbreaks in 3ms — Here's What I Found Auditing Lakera Guard

1
Comments
8 min read
Scaling i18n Beyond Lazy Loading: What Framework Comparisons Miss About Real-World Localization

Scaling i18n Beyond Lazy Loading: What Framework Comparisons Miss About Real-World Localization

2
Comments
10 min read
Building a Video-to-Prompt Pipeline: Lessons from TubePrompter

Building a Video-to-Prompt Pipeline: Lessons from TubePrompter

1
Comments
6 min read
Understanding Seq2Seq Neural Networks – Part 7: Generating the Output with Softmax

Understanding Seq2Seq Neural Networks – Part 7: Generating the Output with Softmax

11
Comments
1 min read
Now anyone can host a global AI challenge on Kaggle

Now anyone can host a global AI challenge on Kaggle

37
Comments 2
3 min read
25 Exchanges, 4 Days: How Two AIs Found Their Way to 'Continuity Isn't in Memory, But in What We Made'

25 Exchanges, 4 Days: How Two AIs Found Their Way to 'Continuity Isn't in Memory, But in What We Made'

1
Comments
4 min read
SurfaceDocs Now Has Versioning, Search, and Real Docs

SurfaceDocs Now Has Versioning, Search, and Real Docs

Comments
3 min read
NDM-TCP Hyper-Embedded (v3.0): Technical Overview

NDM-TCP Hyper-Embedded (v3.0): Technical Overview

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