Cobus Greyling (8)

RAG, Data Privacy, Attack Methods & Safe-Prompts

Cobus Greyling

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

Time-Aware Adaptive RAG (TA-ARE)

Cobus Greyling

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

Proxy Fine-Tuning LLMs

Cobus Greyling

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?

Cobus Greyling

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

There are a...

T-RAG = RAG + Fine-Tuning + Entity Detection

Cobus Greyling

The T-RAG approach is premised on combining RAG architecture with an open-source fine-tuned LLM and an entities tree ...

LLM Drift, Prompt Drift & Cascading

Cobus Greyling

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

The Shifting Vocabulary of AI

Cobus Greyling

The vocabulary in Generative AI and Conversational AI is evolving at a rapid pace. The challenge with such swift...

The Case For Small Language Models

Cobus Greyling

Considering Conversational AI implementations in general, like chatbots and voicebots, making use of a Large...

Beyond Chain-of-Thought LLM Reasoning

Cobus Greyling

This approach can be implemented on a prompt level and does not require any dedicated frameworks or pre-processing.

A...

Comparing Human, LLM & LLM-RAG Responses

Cobus Greyling

Kore.ai Technical Blog

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)

Proxy Fine-Tuning LLMs

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

Fine-Tuning or RAG?

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

T-RAG = RAG + Fine-Tuning + Entity Detection

The T-RAG approach is premised on combining RAG architecture with an open-source fine-tuned LLM and an entities tree ...

LLM Drift, Prompt Drift & Cascading

The Shifting Vocabulary of AI

The Case For Small Language Models

Beyond Chain-of-Thought LLM Reasoning

This approach can be implemented on a prompt level and does not require any dedicated frameworks or pre-processing.

Comparing Human, LLM & LLM-RAG Responses

A recent study, focusing on the healthcare & preoperative medicine compared expert human feedback with LLM...

Leave Comment

Products

XO Capabilities

Solutions

Industries

Developers

RESOURCES

Support

Let’s work together