Cobus Greyling (3)

Prompt-RAG

Vector Embedding Free Retrieval-Augmented Generation

While Prompt-RAG does come with its limitations, it can...

Please Stop Saying Long Context Windows Will Replace RAG

And I’m curious to know if anyone has innovative approaches to using long context windows efficiently?

Long Context...

LLMs Training SLMs

Research from Microsoft Research shows how they used LLMs to train SLMs without any RLHF…

The primary focus in training...

The Evolution of Grounding & Planning In AI Agents

Simply put, intents are categories or classes used to classify conversations.Each interaction between a user and the...

The Shift From Large Language Models to Smaller, Vision-Enhanced Models & The Rise of AI Agents— Version 6

In recent developments within AI research, the focus has gradually shifted from reliance on Large Language Models...

LLM Drift, Prompt Drift & Cascading

Prompt Chaining can be performed manually or automatically; manual entails crafting chains by hand, via a GUI chain...

RAG, Data Privacy, Attack Methods & Safe-Prompts

A fairly recent study explored RAG security vulnerabilities and ways in which private data can be accessed via...

Time-Aware Adaptive RAG (TA-ARE)

With the advent of Large Language Models (LLMs) there was the concept of emergent capabilities. The premise or...

Proxy Fine-Tuning LLMs

Proxy fine-tuning achieves the results of directly tuning a LLM, but by accessing only its prediction…

But first let’s...

Fine-Tuning or RAG?

Comparing different LLM knowledge injection methods…Fine-Tuning or RAG? The short answer is, it depends…

There are a...