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.
PPO vs DPO vs GRPO: which RL method should you use?

PPO vs DPO vs GRPO: which RL method should you use?

Comments
8 min read
How we measure the real CEFR level of a book, and where it still fails

How we measure the real CEFR level of a book, and where it still fails

Comments
3 min read
Vietnam AI & LLM Daily Briefing (Nov 04, 2026)

Vietnam AI & LLM Daily Briefing (Nov 04, 2026)

Comments
4 min read
Điểm tin Trí tuệ Nhân tạo & Mô hình Ngôn ngữ lớn (LLMs) tại Việt Nam (04/11/2026)

Điểm tin Trí tuệ Nhân tạo & Mô hình Ngôn ngữ lớn (LLMs) tại Việt Nam (04/11/2026)

Comments
9 min read
A beginner's guide to the Qwen-Image-2.1-Turbo-Quantized model by Abenzerps on Huggingface

A beginner's guide to the Qwen-Image-2.1-Turbo-Quantized model by Abenzerps on Huggingface

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
Independent study tests Direct Nash Optimization for aligning language models

Independent study tests Direct Nash Optimization for aligning language models

Comments
1 min read
I rebuilt a 1.47 MB, 761,000-parameter intent router and raced it against if statements. The if statements won

I rebuilt a 1.47 MB, 761,000-parameter intent router and raced it against if statements. The if statements won

Comments
12 min read
GPT-6 AstraがQwen3.5-0.8Bを重みの0.016%編集で修正した方法

GPT-6 AstraがQwen3.5-0.8Bを重みの0.016%編集で修正した方法

Comments
4 min read
Bagaimana GPT-6 Astra Memperbaiki Qwen3.5-0.8B dengan Mengedit 0,016% Bobotnya

Bagaimana GPT-6 Astra Memperbaiki Qwen3.5-0.8B dengan Mengedit 0,016% Bobotnya

Comments
9 min read
GPT-6 Astra แก้ไข Qwen3.5-0.8B ได้อย่างไร ด้วยการแก้ไขน้ำหนักโมเดลเพียง 0.016%

GPT-6 Astra แก้ไข Qwen3.5-0.8B ได้อย่างไร ด้วยการแก้ไขน้ำหนักโมเดลเพียง 0.016%

Comments
5 min read
How I Made a 27‑Billion‑Parameter Model Run on My MacBook Pro in Real Time – And Debugged It Live!

How I Made a 27‑Billion‑Parameter Model Run on My MacBook Pro in Real Time – And Debugged It Live!

Comments
7 min read
Introducing SynthID Bio

Introducing SynthID Bio

Comments
1 min read
We tested the viral AI chart model on dates it can't have seen. No edge.

We tested the viral AI chart model on dates it can't have seen. No edge.

Comments
5 min read
LoRA vs QLoRA: which should you use to fine-tune an LLM?

LoRA vs QLoRA: which should you use to fine-tune an LLM?

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