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.
Hillock: A brain-inspired, CPU-bound memory gate for local LLMs

Hillock: A brain-inspired, CPU-bound memory gate for local LLMs

1
Comments
2 min read
Does Quantization Break Tool-Calling? I Measured It on a 4GB Laptop GPU (BFCL, 3 Seeds, Bootstrap 95% CI)

Model family outperforms size as a predictor

Does Quantization Break Tool-Calling? I Measured It on a 4GB Laptop GPU (BFCL, 3 Seeds, Bootstrap 95% CI)

3
Comments 10
4 min read
Documents Aren't Bags of Chunks

Documents Aren't Bags of Chunks

15
Comments 35
3 min read
How Developers Really Use AI: Claude, Codex, and the Skills Debate

How Developers Really Use AI: Claude, Codex, and the Skills Debate

1
Comments
1 min read
Optimal Transport Converts Dense Layers to Sparse Experts

Optimal Transport Converts Dense Layers to Sparse Experts

Comments
2 min read
Vector Databases Are Not Magic, Here's What's Actually Happening Under the Hood

Vector Databases Are Not Magic, Here's What's Actually Happening Under the Hood

Comments
9 min read
AI Agents in Production: Structured Generation for AI Workflows

AI Agents in Production: Structured Generation for AI Workflows

Comments
6 min read
Building a RAG pipeline in a weekend

Building a RAG pipeline in a weekend

1
Comments
4 min read
FutureX · Physical AI Daily — Issue 28 (06/15)

FutureX · Physical AI Daily — Issue 28 (06/15)

Comments
14 min read
# Your AI Agent Is a Distributed System in Disguise — Instrument It with OpenTelemetry and SigNoz Before It Bankrupts You

# Your AI Agent Is a Distributed System in Disguise — Instrument It with OpenTelemetry and SigNoz Before It Bankrupts You

1
Comments 2
7 min read
In multi-agent systems, the skill is the abstraction level — not the agent count

In multi-agent systems, the skill is the abstraction level — not the agent count

2
Comments 1
4 min read
NVIDIA RTX Spark Superchip: Unified CPU–GPU Memory

NVIDIA RTX Spark Superchip: Unified CPU–GPU Memory

Comments 1
8 min read
Gemini Prototyping, AI Code Migration Agents, and LLM Transparency Insights

Gemini Prototyping, AI Code Migration Agents, and LLM Transparency Insights

Comments
4 min read
You Don't Need a Better Agent. You Need a Better Debug Loop.

You Don't Need a Better Agent. You Need a Better Debug Loop.

1
Comments
2 min read
The Whole Paper Fits in One Sigmoid: Implementing the SDAR Gate

The Whole Paper Fits in One Sigmoid: Implementing the SDAR Gate

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