Table of Contents

AI Large Language Models (LLMs)

see also:

Introduction

  • whilst they are useful in the short term, current LLMs only simulate intelligence and they have major flaws
    • most have a knowledge cut off date as to end of the acquisition of data for their training
    • whilst they have a massive amount of knowledge accumulation this does not substitute for actual understanding
    • they memorize lots of “problem statements” and “recipes” on how to solve them
    • if needing to solve a new problem they will use the closest matching “recipe” even if this is not logical and usually without checking the solution for logic, common sense or real world modelling checks - and if it gives an incorrect response, it will generally reply “I'm sorry, you are right” and apply another irrelevant recipe.
    • responses are very dependent upon:
      • its data on which it was trained (quality and quantity)
      • how it was trained and fine tuned
      • its context length
      • it's temperature creativity hyper-parameter setting
      • its hidden system prompts (these are usually designed to provide guardrails)
      • how your prompts are provided (role instructions, where to source information, how to format it, whether you have included irrelevant information which it may think is more important, etc)

Performance measures

Current models

Google DeepMind's Chinchilla LLM

OpenAI's GPT

Meta's Llama

Google's Gemini

Microsoft's Phi

Mistral

Private GTP

Other ways to ingest local documents into a local LLM

Other ways to run downloaded LLMs on your computer offline

Running multimodal image2txt LLMs on your computer offline

Prompt engineering

Fine tuning models to particular tasks or domains

LoRA (Low-Rank Adaptation of Large Language Models)

Vector embeddings

Hallucination mitigation

Improving performance using AI iterative Agents