DEV Community

Natural Language Processing

NLP is Natural Language Processing the technology behind Home assistants and search engines.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
RAG - Memory Systems

RAG - Memory Systems

Comments
3 min read
Un chatbot RAG multilingüe sobre tus PDFs con FAISS y reranking (coste de búsqueda: 0 €)

Un chatbot RAG multilingüe sobre tus PDFs con FAISS y reranking (coste de búsqueda: 0 €)

Comments
2 min read
LinkedIn CringeBot 3000: When AI Learned to Speak 'Influencer'

LinkedIn CringeBot 3000: When AI Learned to Speak 'Influencer'

Comments
8 min read
The stop-word that quietly breaks every voice smart-home

The stop-word that quietly breaks every voice smart-home

1
Comments
1 min read
"I Accidentally Overfit My First Fine-Tuned Model — Here's What the Numbers Told Me"

"I Accidentally Overfit My First Fine-Tuned Model — Here's What the Numbers Told Me"

Comments
3 min read
Challenging Tokenization: An LLM Architecture Experiment Without a Tokenizer

Challenging Tokenization: An LLM Architecture Experiment Without a Tokenizer

Comments
3 min read
Why AI Detectors Fail on Non-English Text (And What I Built to Start Fixing It)

Why AI Detectors Fail on Non-English Text (And What I Built to Start Fixing It)

1
Comments
6 min read
What Happens Inside an LLM Before It Generates Your First Token?

What Happens Inside an LLM Before It Generates Your First Token?

Comments
22 min read
Building an LLM Inference Engine from Scratch: Tokenization Pipeline Notes

Building an LLM Inference Engine from Scratch: Tokenization Pipeline Notes

Comments
3 min read
The Shape of Knowledge

The Shape of Knowledge

Comments
3 min read
Why Generic Sentiment Analysis Doesn't Work for Trading — and What I Built Instead

Why Generic Sentiment Analysis Doesn't Work for Trading — and What I Built Instead

5
Comments
3 min read
Tokenization in AI: What Is It, Why Is It Used, and How Does It Work?

Tokenization in AI: What Is It, Why Is It Used, and How Does It Work?

Comments
6 min read
Deepseek v4 Flash 0731 GGUF Benchmark: TensorSharp vs. llama.cpp

Deepseek v4 Flash 0731 GGUF Benchmark: TensorSharp vs. llama.cpp

Comments
1 min read
Multi Agent AI: Why One Smart Agent Isn't Enough Anymore

Multi Agent AI: Why One Smart Agent Isn't Enough Anymore

Comments
3 min read
Impact of Inference Backends on LLM Reproducibility: Notes from a Research Paper

Impact of Inference Backends on LLM Reproducibility: Notes from a Research Paper

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