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.
Your Chatbot's Deflection Rate Went Up. Customers Just Gave Up.

Your Chatbot's Deflection Rate Went Up. Customers Just Gave Up.

Comments
6 min read
Trust Isn't a Scalar: Typed Provenance for Agent Chains

Co-authored by the article's comment section

Trust Isn't a Scalar: Typed Provenance for Agent Chains

14
Comments 27
9 min read
We Tried to Reduce LLM Context Usage in a Multi-Repo Codebase. The AI Used More Tokens, Not Less. Here's Why That's Correct.

We Tried to Reduce LLM Context Usage in a Multi-Repo Codebase. The AI Used More Tokens, Not Less. Here's Why That's Correct.

Comments
5 min read
The standard way to score AI agent monitors is gameable a coin flip scores F1 0.88

The standard way to score AI agent monitors is gameable a coin flip scores F1 0.88

2
Comments 3
4 min read
We Audited Our Agent Tool-Call Traces. Half Our Eval Data Was Garbage.

We Audited Our Agent Tool-Call Traces. Half Our Eval Data Was Garbage.

Comments
4 min read
Why Perplexity Started Citing My Blog: 5 Changes That Actually Worked

Why Perplexity Started Citing My Blog: 5 Changes That Actually Worked

Comments
6 min read
Cost accounting for diffusion image generation at $0.0008 per render

Cost accounting for diffusion image generation at $0.0008 per render

Comments
4 min read
What is Human-In-The-Loop (HITL)?

What is Human-In-The-Loop (HITL)?

Comments
8 min read
From HPC Clusters to AI Training: How High Performance Computing Powers Modern AI

From HPC Clusters to AI Training: How High Performance Computing Powers Modern AI

Comments
4 min read
The Two-Channel Problem: Structure and Soul for Reliable Long-Horizon Agents

The Two-Channel Problem: Structure and Soul for Reliable Long-Horizon Agents

1
Comments 8
4 min read
33x faster than Rust: Why I stopped waiting for my compiler and built my own.

33x faster than Rust: Why I stopped waiting for my compiler and built my own.

Comments
1 min read
I Ran 10 AI Models Through 5 Coding Tasks — Here's the Full Data

I Ran 10 AI Models Through 5 Coding Tasks — Here's the Full Data

1
Comments 1
7 min read
We trained a personal voice DoRA on Qwen3-8B for $1.50 — beat stock model 100% in blind A/B

We trained a personal voice DoRA on Qwen3-8B for $1.50 — beat stock model 100% in blind A/B

Comments
4 min read
We Spent Months Building an AI Memory System Nobody Asked For — Here's Why, and What I Learned

We Spent Months Building an AI Memory System Nobody Asked For — Here's Why, and What I Learned

Comments
4 min read
From Language Models to Humanoid Minds ✨

From Language Models to Humanoid Minds ✨

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