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 much VRAM do you actually need to run Llama 3 or Gemma locally?

How much VRAM do you actually need to run Llama 3 or Gemma locally?

Comments
4 min read
Kimi K3 wins cyber audits over US models as safety chief abruptly resigns

Kimi K3 wins cyber audits over US models as safety chief abruptly resigns

8
Comments
10 min read
[AI] Practical QLoRA Fine-tuning: Axolotl & Unsloth | SLM Playbook

[AI] Practical QLoRA Fine-tuning: Axolotl & Unsloth | SLM Playbook

1
Comments
6 min read
I made my agent more capable and it got worse

I made my agent more capable and it got worse

1
Comments
4 min read
Developer Take On: A High-Resolution Neural Cellular Automata

Developer Take On: A High-Resolution Neural Cellular Automata

Comments
4 min read
I Built a World Cup 2026 Prediction Pipeline with Sportmicro, Python, and GitHub Actions

I Built a World Cup 2026 Prediction Pipeline with Sportmicro, Python, and GitHub Actions

2
Comments 3
4 min read
Semantic Drift in LLMs: How Archetypal Attractors (Like “Goblin”) Emerge and How Structured Reflection Reduces Them

Semantic Drift in LLMs: How Archetypal Attractors (Like “Goblin”) Emerge and How Structured Reflection Reduces Them

6
Comments 1
5 min read
k-means from scratch, and why it sometimes lies

k-means from scratch, and why it sometimes lies

Comments 2
3 min read
I Watched Two AI Agents Invent Their Own Language

I Watched Two AI Agents Invent Their Own Language

1
Comments
3 min read
FutureX · Physical AI Daily — Issue 35 (06/22)

FutureX · Physical AI Daily — Issue 35 (06/22)

1
Comments
11 min read
Mid-Command Language Switching Broke Our Voice Pipeline: Here Is What We Changed

Mid-Command Language Switching Broke Our Voice Pipeline: Here Is What We Changed

1
Comments 1
4 min read
Vibe citing: how KPMG used AI to write a report about AI and AI made them look like fools

Vibe citing: how KPMG used AI to write a report about AI and AI made them look like fools

Comments
6 min read
I Gave 3 AI Agents a Decaying Notepad and They Built a Culture

I Gave 3 AI Agents a Decaying Notepad and They Built a Culture

1
Comments 1
3 min read
Hillock: A brain-inspired, CPU-bound memory gate for local LLMs

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

Comments
2 min read
Open-Source LLM APIs Beat Self-Hosting. Here's the Math.

Open-Source LLM APIs Beat Self-Hosting. Here's the Math.

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