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.
30/60 Days System Design Questions!

30/60 Days System Design Questions!

1
Comments 5
2 min read
What it actually costs to generate one AI cartoon video, line by line

What it actually costs to generate one AI cartoon video, line by line

1
Comments 4
9 min read
What Happens Inside an LLM During Inference: Tokens, KV Cache, and GPU Execution Explained

What Happens Inside an LLM During Inference: Tokens, KV Cache, and GPU Execution Explained

Comments
12 min read
# Multi-Head Latent Attention (MLA)

# Multi-Head Latent Attention (MLA)

Comments
9 min read
Introduction to Generative AI

Introduction to Generative AI

Comments
2 min read
Matt Turck 对话了OpenAI 强化学习基础团队(Foundations of Reinforcement Learning)主管 Dan Roberts

Matt Turck 对话了OpenAI 强化学习基础团队(Foundations of Reinforcement Learning)主管 Dan Roberts

Comments
2 min read
Every Step Was Allowed. The Sequence Was the Attack. (AI Memory Judgment, CLAIM-30)

Logic joins bypassing per-step gates

Every Step Was Allowed. The Sequence Was the Attack. (AI Memory Judgment, CLAIM-30)

15
Comments 65
7 min read
We Should Have Never Built That Treasure Hunt Engine — A Postmortem

We Should Have Never Built That Treasure Hunt Engine — A Postmortem

Comments 1
3 min read
Tile Extractor

Tile Extractor

Comments
3 min read
S-Scale Operational Prototype Layer v0.1 is now officially published on Zenodo.

S-Scale Operational Prototype Layer v0.1 is now officially published on Zenodo.

Comments
1 min read
Multi-Head Latent Attention (MLA)

Multi-Head Latent Attention (MLA)

Comments
9 min read
# Introduction to Machine Learning: How We Arrive at Linear Regression

# Introduction to Machine Learning: How We Arrive at Linear Regression

Comments
2 min read
Power analysis for LLM evals: how big does your eval set need to be to catch a 5% regression?

Power analysis for LLM evals: how big does your eval set need to be to catch a 5% regression?

1
Comments 1
2 min read
Most AI projects fail in production. It's rarely the model.

Most AI projects fail in production. It's rarely the model.

Comments 1
4 min read
Anthropic API Learnings, Claude Code Structural Blindspots & AI Agent Security Red Team

Anthropic API Learnings, Claude Code Structural Blindspots & AI Agent Security Red Team

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