Differences

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

--- lctg_ai_talk_june2025 [2025.06.04 08:36] – created Steve Isenberg
+++ lctg_ai_talk_june2025 [2025.06.09 17:06] (current) – Steve Isenberg
@@ Line 1: / Line 1: @@
+~~NOCACHE~~ <fc #a0a0a0><fs small>This page last changed ~~LASTMOD~~ [{{counter|today| time| times}} today, {{counter|yesterday| time| times}} yesterday, and {{counter|total| time| total times}}]</fs></fc>
+<fs large>This is material in support of the 6/11/2025 presentation and I expect that it will be updated and changed</fs>.
+References in addition to what is on this page:
+  * [[ai_papers|Comparison of AI engines]]
+  * [[ai_questions|Questions to ask AI engines]]
+  * [[https://www.washingtonpost.com/technology/2025/06/04/ai-summarizers-analysis-test-documents-books/|Washington Post comparison 6/4/2025]] [[washpost20250604|summary]]
-AI Presentation Outline: Exploring AI Engines and Beyond
+  * [[https://www.youtube.com/shorts/rVlmbhwn0RM|(2m) Composing queries: Be polite to AI]]
+  * [[https://www.youtube.com/watch?v=KrV6ldHymwQ|(7m) ChatGPT vs Gemini vs Copilot: Best AI Chatbot in 2025]]
+  * [[https://www.youtube.com/watch?v=dyLTusgZ2NE|(9m) Which AI Chatbot should we pay for? ChatGPT, Claude, Gemini, Grok, Copilot, or Perplexity]]
+  * Poe
+=====AI Presentation Outline: Exploring AI Engines and Beyond=====
 This outline is designed for a presentation to the Lexington Computer Group, incorporating the topics and suggestions discussed in recent emails. It emphasizes practical demonstrations and a comparison of current AI tools, while also delving into more advanced concepts.
-I. Introduction (5-10 minutes)
+====I. Introduction (5-10 minutes)====
-A. Welcome and Context:
+===A. Welcome and Context:===
-Briefly introduce the purpose of the presentation: to explore the landscape of current AI engines and discuss their capabilities and implications.
+  * Briefly introduce the purpose of the presentation: to explore the landscape of current AI engines and discuss their capabilities and implications.
+  * Acknowledge the group's interest in AI and the collaborative nature of this topic (as suggested by recent email discussions).
-Acknowledge the group's interest in AI and the collaborative nature of this topic (as suggested by recent email discussions).
+===B. “Let Me Sum Up”===
-B. “Let Me Sum Up” (as inspired by John Rudy):
+  * Acknowledge the rapid evolution of AI and the need to understand its various facets.
+  * Briefly touch upon the presenters' journey into understanding AI.
-Acknowledge the rapid evolution of AI and the need to understand its various facets.
+===C. Presentation Goals:===
-Briefly touch upon the presenters' journey into understanding AI, perhaps mentioning the BOLLI AI course.
+  * To provide a comparison of popular AI chatbots.
+  * To demonstrate practical applications and advanced features of AI.
+  * To foster discussion and shared learning within the group.
-C. Presentation Goals:
+Note: AI Chatbot = AI Bot = AI Engine
-To provide a comparison of popular AI chatbots.
+====II. Comparing the Chatbots: Strengths and Experiences (20-25 minutes)====
+===A. Overview of Selected Chatbots:===
-To demonstrate practical applications and advanced features of AI.
+  * Comparison paper
+  * Washington Post summary
-To foster discussion and shared learning within the group.
+===B. Live Demonstration & Comparison (Heavy Emphasis):===
-II. Comparing the Chatbots: Strengths and Experiences (20-25 minutes)
+  * Discussion. Attendees impression of Strengths (from experience):
-A. Overview of Selected Chatbots:
+    * Share personal insights on which chatbot excels in specific areas (e.g., creativity, factual accuracy, coding, conversational flow).
+    * Discuss user interface and ease of use.
+  * Sentiment Analysis Comparison:
+    * Briefly present findings or a live demonstration of how different AI engines respond to sentiment analysis queries, as Peter Albin explored with Perplexity.
-Briefly introduce Chat GPT, Claude, and Gemini.
+====III. Beyond Basic Chat: Advanced AI Capabilities (20-25 minutes)====
+===A. Retrieval Augmented Generation (RAG) Technology:===
-Highlight their general purpose and key differentiating philosophies (if any).
+  * Concept Explanation: Use visualizations to explain what RAG is and why it's important for overcoming AI hallucinations and providing more accurate, grounded responses.
+  * Demonstration: Show an example of an AI (e.g., Gemini) leveraging RAG to answer a question by citing specific sources or external knowledge.
-B. Live Demonstration & Comparison (Heavy Emphasis):
+===B. Deep Research Capability:===
-Interactive Demos: For each chatbot, perform a standard set of tasks (as suggested by Harry Forsdick).
+  * Concept Explanation: Discuss how AI can be used for in-depth research, going beyond simple search queries.
+  * Demonstration: Showcase a “Deep Research” session (as John Day mentioned using Gemini for the energy consumption report).
+    * Walk through the process of posing a complex query.
+    * Show how the AI gathers and synthesizes information from multiple sources.
+    * Present the results and discuss their utility.
-Example Tasks:
+===C. Programming with AI to Overcome Ambiguity:===
-Generating creative text (e.g., a short story, a poem).
+  * Concept Explanation: Address the challenge of ambiguity in generative AI responses and how programmatic approaches can help refine and control outputs.
+  * Demonstration: Provide a simple example of using AI for programming tasks, perhaps demonstrating how to refine a prompt or use structured output to get a more precise response.
-Summarizing a complex article.
+====IV. Q&A and Open Discussion (15-20 minutes)====
+===A. Facilitated Discussion:===
-Answering factual questions.
+  * Open the floor for questions from the group.
+  * Encourage attendees to share their own experiences with AI tools.
+  * Discuss potential future topics for the group related to AI.
+  *
+===B. Future Outlook:===
-Performing a simple coding task or debugging.
+  * Briefly touch upon the ongoing advancements in AI and what the future might hold.
+  * Emphasize the importance of continuous learning in this rapidly evolving field.
-Discussion of Strengths (from experience):
+====V. Conclusion (5 minutes)====
+===A. Key Takeaways:===
-Share personal insights on which chatbot excels in specific areas (e.g., creativity, factual accuracy, coding, conversational flow).
+  * Reiterate the main points: AI tools offer diverse strengths, and advanced techniques like RAG and deep research enhance their utility.
+  * The importance of hands-on experience and critical evaluation.
-Discuss user interface and ease of use.
+===B. Thank You and Next Steps:===
-Sentiment Analysis Comparison (Peter Albin's contribution):
+  * Thank the audience for their participation.
+  * Suggest resources for further exploration (e.g., specific AI platforms, online courses).
-Briefly present findings or a live demonstration of how different AI engines respond to sentiment analysis queries, as Peter Albin explored with Perplexity.
+  * Invite continued discussion within the Lexington Computer Group.
-III. Beyond Basic Chat: Advanced AI Capabilities (20-25 minutes)
-A. Retrieval Augmented Generation (RAG) Technology:
-Concept Explanation: Use visualizations to explain what RAG is and why it's important for overcoming AI hallucinations and providing more accurate, grounded responses.
-Demonstration: Show an example of an AI (e.g., Gemini) leveraging RAG to answer a question by citing specific sources or external knowledge.
-B. Deep Research Capability:
-Concept Explanation: Discuss how AI can be used for in-depth research, going beyond simple search queries.
-Demonstration: Showcase a “Deep Research” session (as John Day mentioned using Gemini for the energy consumption report).
-Walk through the process of posing a complex query.
-Show how the AI gathers and synthesizes information from multiple sources.
-Present the results and discuss their utility.
-C. Programming with AI to Overcome Ambiguity:
-Concept Explanation: Address the challenge of ambiguity in generative AI responses and how programmatic approaches can help refine and control outputs.
-Demonstration: Provide a simple example of using AI for programming tasks, perhaps demonstrating how to refine a prompt or use structured output to get a more precise response.
-IV. Q&A and Open Discussion (15-20 minutes)
-A. Facilitated Discussion:
-Open the floor for questions from the group.
-Encourage attendees to share their own experiences with AI tools.
-Discuss potential future topics for the group related to AI.
-B. Future Outlook:
-Briefly touch upon the ongoing advancements in AI and what the future might hold.
-Emphasize the importance of continuous learning in this rapidly evolving field.
-V. Conclusion (5 minutes)
-A. Key Takeaways:
-Reiterate the main points: AI tools offer diverse strengths, and advanced techniques like RAG and deep research enhance their utility.
-The importance of hands-on experience and critical evaluation.
-B. Thank You and Next Steps:
-Thank the audience for their participation.
-Suggest resources for further exploration (e.g., specific AI platforms, online courses).
-Invite continued discussion within the Lexington Computer Group.
 Visuals & Style Notes:
-Use a mixture of high-level visualizations for concepts and live, on-line demonstrations (heavy emphasis on demos).
+  * Use a mixture of high-level visualizations for concepts and live, on-line demonstrations (heavy emphasis on demos).
+  * Keep explanations concise and focus on illustrating capabilities through practical examples.
-Keep explanations concise and focus on illustrating capabilities through practical examples.
+  * Maintain an engaging and interactive tone.
-Maintain an engaging and interactive tone.