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.
Evolutionary selection boosts LLM agent performance

Evolutionary selection boosts LLM agent performance

Comments
3 min read
Rerankers overlook 55% coordination failures

Rerankers overlook 55% coordination failures

Comments
2 min read
GPT-5.6 Sol Is the Best 'Vision' Model OpenAI Ever Released — and Roboflow's Benchmarks Prove It

GPT-5.6 Sol Is the Best 'Vision' Model OpenAI Ever Released — and Roboflow's Benchmarks Prove It

Comments
4 min read
The Benchmarkpocalypse: Why AI Benchmarks Are Broken — and What Dan Luu Says We Should Do About It

The Benchmarkpocalypse: Why AI Benchmarks Are Broken — and What Dan Luu Says We Should Do About It

1
Comments
4 min read
How I Engineered the World's First Khattak Pashto LLM (Qwen2 + LoRA)

How I Engineered the World's First Khattak Pashto LLM (Qwen2 + LoRA)

Comments
3 min read
Gemma 4 on a Tesla T4: QAT Weights Decode 1.79x Faster Than bf16

Gemma 4 on a Tesla T4: QAT Weights Decode 1.79x Faster Than bf16

8
Comments 1
9 min read
The Scrape-First Era Is Over: Your Training Data Is a Supply Chain Now

The Scrape-First Era Is Over: Your Training Data Is a Supply Chain Now

Comments
6 min read
Reading a small model's confidence instead of its prose

Reading a small model's confidence instead of its prose

Comments 1
2 min read
Teaching our on-device assistant to say "I don't know"

Teaching our on-device assistant to say "I don't know"

Comments 4
3 min read
DeepSeek vs Qwen vs Kimi vs GLM: Which One Should You Use?

DeepSeek vs Qwen vs Kimi vs GLM: Which One Should You Use?

Comments
7 min read
The Most Important Feature of a Legal AI Might Be Knowing When Not to Answer

The Most Important Feature of a Legal AI Might Be Knowing When Not to Answer

Comments 1
3 min read
Approximate Inference: Sampling the Posterior vs Optimizing an Approximation

Approximate Inference: Sampling the Posterior vs Optimizing an Approximation

Comments
7 min read
I Built an Agentic AI System From Scratch: RAG, GraphRAG, 12 Tools & Kubernetes

I Built an Agentic AI System From Scratch: RAG, GraphRAG, 12 Tools & Kubernetes

Comments
9 min read
GPTZero stopped using perplexity in 2023 and the internet kept explaining it

GPTZero stopped using perplexity in 2023 and the internet kept explaining it

1
Comments 1
3 min read
Two prompts moved seven AI detectors by fifty points

Two prompts moved seven AI detectors by fifty points

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