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.
Picking the longest answer scores 43% on OpenBookQA and ~chance on ARC: a per-benchmark length-shortcut census

Picking the longest answer scores 43% on OpenBookQA and ~chance on ARC: a per-benchmark length-shortcut census

Comments
4 min read
Running DiffusionGemma Locally on an RTX 5090 with vLLM: The One-Time Pioneer Cost of Bleeding-Edge Model Bleeding-Edge GPU

Running DiffusionGemma Locally on an RTX 5090 with vLLM: The One-Time Pioneer Cost of Bleeding-Edge Model Bleeding-Edge GPU

Comments
4 min read
Your MCP Tools Are Leaking: A Benchmark for Description Canonicalisation

Your MCP Tools Are Leaking: A Benchmark for Description Canonicalisation

Comments
3 min read
Your Question-Level Split Can Leak the Same Answer Twice

Your Question-Level Split Can Leak the Same Answer Twice

1
Comments 5
7 min read
LLM Research Blog: The Model that Fits our Project

LLM Research Blog: The Model that Fits our Project

Comments
4 min read
Sixteen JAX devices on a CPU, and one gradient bug worth finding

Sixteen JAX devices on a CPU, and one gradient bug worth finding

Comments
4 min read
Safety Rules Don’t Survive the Context Window: Quantifying and Fixing Agent Compliance Decay

Safety Rules Don’t Survive the Context Window: Quantifying and Fixing Agent Compliance Decay

Comments
6 min read
I Built EveryO to Understand How Neural Networks Actually Work

I Built EveryO to Understand How Neural Networks Actually Work

Comments
8 min read
How do you know your company matching is right? We had to grade the grader

How do you know your company matching is right? We had to grade the grader

Comments
3 min read
Real-looking people in a product video, for $0, on a MacBook: I tested 5 methods

Real-looking people in a product video, for $0, on a MacBook: I tested 5 methods

Comments
12 min read
What a Right Answer Costs

What a Right Answer Costs

Comments
4 min read
AI news roundup — morning, 26 Oct 2026: an agent past a paywall, $40B for chips, and Elvis's estate vs Anthropic

AI news roundup — morning, 26 Oct 2026: an agent past a paywall, $40B for chips, and Elvis's estate vs Anthropic

Comments
7 min read
Exploring Open-Source Large Language Models: Choosing the Right Model for MiniChefGPT

Exploring Open-Source Large Language Models: Choosing the Right Model for MiniChefGPT

1
Comments
6 min read
What Actually Happens When a Transformer Thinks Step by Step: The Mechanics of Chain-of-Thought

What Actually Happens When a Transformer Thinks Step by Step: The Mechanics of Chain-of-Thought

Comments
5 min read
When Latency Becomes A Training Data Defect

When Latency Becomes A Training Data Defect

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