The "To Keep Up" Wiki

A collection of information we find useful

User Tools

Site Tools


lctg:20231018plus-details

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
lctg:20231018plus-details [2023.09.21 13:43] – created Steve Isenberglctg:20231018plus-details [2023.10.18 08:01] (current) Steve Isenberg
Line 1: Line 1:
-====Details on Conor O'Mahony's October 2023 Talks====+~~NOCACHE~~ //<fs x-small>This page last changed ~~LASTMOD~~ and viewed {{counter|today| time| times}} today, {{counter|yesterday| time| times}} yesterday, and {{counter|total| time| total times}} since 9/21/2023.</fs>//\\  
 +//Details on Conor O'Mahony's October/November 2023 Talks//
  
 ====A Topdown Look at ChatGPT==== ====A Topdown Look at ChatGPT====
-Conor O'Mahony\\  +Presented by Conor O'Mahony\\ \\  
-Presented October 2023 to the Lexington Computer and Technology Group +Join us for three Wednesday morning meetings in October and November 2023, presented in conjunction with the Lexington Computer and Technology Group\\ \\ Wednesdays October 18, 25, and November 1, 10:00am - 11:30am ET.\\  //Presented live in the Lexington Community Center and live online via Zoom.\\  These will be recorded for later viewing.//
- +
-//Note: This summary was written by Harry Forsdick based on a conversation with Conor about his talks.  Conor has not seen this (he's on vacation) so, like ChatGPT, I may be making some of this up...  -- HF// +
  
 One of the problems in trying to understand how ChatGPT works is that we have all heard a variety of incomplete explanations and are left on our own to figure out the missing pieces.  This set of talks will step back and introduce ChatGPT methodically by presenting a top-down look at ChatGPT.  The talks will attempt to show how several different mechanisms are integrated together to yield the intelligent assistant we would all like to have. One of the problems in trying to understand how ChatGPT works is that we have all heard a variety of incomplete explanations and are left on our own to figure out the missing pieces.  This set of talks will step back and introduce ChatGPT methodically by presenting a top-down look at ChatGPT.  The talks will attempt to show how several different mechanisms are integrated together to yield the intelligent assistant we would all like to have.
  
-The first talk will look at the goals of the applicationhow to use it, and some examples of actually using it.  Then we will analyze the various tasks ChatGPT must perform in order to be useful.+If you're interested, the GPT in ChatGPT stands for **G**enerative **P**re-Trained **T**ransformer.
  
-**October 18: How to Interact with ChatGPT**+===October 18: How to Interact with ChatGPT===  
 +(no technical knowledge needed)
   * Introduction to ChatGPT   * Introduction to ChatGPT
   * Prompt Engineering: Presenting Results so that you feel like you are in a conversation   * Prompt Engineering: Presenting Results so that you feel like you are in a conversation
  
-The second talk will discuss the nature of the intelligence displayed by ChatGPT.  This will be illustrated by some successful examples that are pretty amazing, and then some unsuccessful examples which give more insight into how ChatGPT works. +===October 25: How Smart is ChatGPT?=== 
- +(no technical knowledge needed) 
-**October 25: How Intelligent is ChatGPT?**+  Training ChatGPT
   * Reasoning, Understanding, and Consciousness   * Reasoning, Understanding, and Consciousness
-  * Deeper Look at ChatGPT 
- 
-The third talk will start with a more complex topic: Training: What do you have to do to introduce knowledge into ChatGPT? What are some of the underpinnings that are the core mechanisms of ChatGPT?  Plus some additional areas of research needed before ChatGPT will be what people expect from a truly intelligent assistant. 
  
-**November 1: Two Additional ChatGPT Topics** +===November 1: How LLMs Work=== 
-  * How ChatGPT is Trained +(a technical presentation) 
-  * Underlying Research that has/will have Made ChatGPT Possible+  * How LLMs, Large Language Models, work
lctg/20231018plus-details.1695329007.txt.gz · Last modified: 2023.09.21 13:43 by Steve Isenberg