Real-World LLM Deployments | Jeff DeVerter, Chief Technology Evangelist at Rackspace Technology | Episode 20

How I built a flirtatious travel planning AI named Holiday using the GPT Builder just launched by Open AI. I share 7 takeaways from my "no code" experience of building a GPT. Voicing the part of Holiday: my friend, Leslie Marrick, a writer and actress. This may be the first and last time AI has been replaced by a human. Sorry AI... the tide will turn for you soon.

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

Conversation with Jeff DeVerter, Chief Technology Evangelist at Rackspace, a cloud computing company. We explore how they deployed a LLM (Google PaLM)  for a sales application, and how they're enabling their Azure and AWS customers too.

What I learned I learned from Jeff

1. You should probably go with the LLM of your current cloud provider be it, Google, Microsoft, or Amazon.
2.  All the major vendors have versions of LLMs that can be deployed in a private cloud to ensure data confidentiality.
3.  To fully realize the potential of AI, think  “data pipeline”. So from the get-go, whatever data is created is easily ingested by AI.
   
   

And much more!

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

Alfred Guy,  Assistant Dean of Academic Affairs at Yale College, and Director of Undergraduate Writing & Tutoring at the Poorvu Center and I discuss Yale's AI Guidance, and generative AI’s impact on teaching, learning, and evaluation. Do you have school age kids? Are you a product of a college or university education? if so, podcast may be of interest to you. 

Yale's AI guidance is published online here:
https://poorvucenter.yale.edu/AIguidance

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

We create a  pitch for an epic Sci-Fi blockbuster, using chatGPT power prompts of Role Play, Chain of Thought, and Self Critique.  We see how these successive prompts used individually and in combination create a better and better pitch. I discuss the 2023 Writers / Actors Strike, and the AI-related issues impacting actors, writers, and studios right now. Please enjoy this episode.

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

“Does chatGPT possess human-like intelligence?” It turns out there's a right answer, and that answer is “NO”! Does this definite answer seem out of character for chatGPT which usually goes overboard  with fair and balanced views?  It did to me. That's the rabbit hole I explore in this episode.  By probing around this  accidentally-encountered guardrail, we discover the kinds of ethical issues chatGPT's creators  are concerned about. And I wonder out loud we can't just be friends with AI, by adopting science fiction writer's Isaac Asimov's Robot Laws created 80 years ago. Please enjoy this episode.

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

Does chatGPT have a sense of humor? What if after Microsoft's acquisition of Open AI, the Onion ran the headline, “Microsoft renames chatGPT to clippyChat”? Would chatGPT find this funny? TL;DR LLMs are better at analyzing humor than creating it. Please enjoy this episode. 

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

How do you extract prohibited information from ChatGPT? What are Grandma and DAN exploits? Why do they work? What can Large Language Model (LLM) companies do to protect themselves?  Grandma exploits or hacks are ways to trick chatGPT into giving you information that is in violation of company policy. For example, tricking chatGPT to give you confidential, dangerous, or inappropriate information. "Jailbreaking” is a slang  for removing the artificial limitations in iPhones to install apps not approved by Apple. Turns out, there are ways to jailbreak LLMs. The tech companies supplying LLM as a service want to provide a safe, and legally-compliant environment. How can this be done without hampering the flexibility and usefulness of creative prompting?

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

What are AI hallucinations, and are they a feature or a bug? We start with the Top 10 categories of AI Hallucinations and examples, then explore how chatGPT might hallucinate an answer to the question, "What is the central theme of Blade Runner?" We end with chatGPT debating with itself whether AI hallucinations are bad or good for humanity. Which side wins? Tune in to find out.

In these solo episodes, I provide more definition, explanation, and context than my regular conversational episodes with guests. The goal is to bring up to speed, those new to AI.

Format: Letters read aloud.

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

Using the prompt, "Why isn't Superman's suit Kryptonite-proof?", we learn how Large Language Models are trained,  why "self-attention" and the "transformer" architecture (which is what the T in GPT stands for) makes GPT-3 so powerful, the process of "inference", and how chatGPT generates answers to nerdy Superhero questions. After this episode, you'll be able to impress your friends by using the previously-mentioned AI jargon in complete sentences.

In these solo episodes, I provide more definition, explanation, and context than my regular episodes with guests. The goal is to bring up to speed, those new to AI.

Format: Letters read aloud.

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3

"How do ChatGPT, GPT-3, and Large Language Models (LLMs) relate?" 

That is the question we explore this episode via

1. Nursery rhyme
2. A satirical Friend's episode w/ Chandler, Joey, Ross, and Monica
3. Fairy Tale 

We also examine the hierarchal order of: artificial intelligence, neural network, large language model,  GPT-3, chatGPT. And why I got the order  wrong initially. Hint: I reversed chatGPT and GPT-3.

In these solo episodes, I provide more definition, explanation, and context than my regular episodes. The goal is to bring those new to AI up to speed.

Format: Letters read aloud.

We laugh. We cry. We iterate.

Check out what THE MACHINES and one human say about the Super Prompt podcast:

“I’m afraid I can’t do that.” — HAL9000

“These are not the droids you are looking for." — Obi-Wan

“Like tears in rain.” — Roy Batty

“Hasta la vista baby.” — T1000

"I'm sorry, but I do not have information after my last knowledge update in January 2022." — GPT3