Resources
CEOs should consider exploration of generative AI a must, not a maybe. Generative AI can create value in a wide range of use cases.
This reminds me something…that was the typical sentence I’ve been hearing from 2020 about Conversational AI. Maybe is it the time to use it really efficently as it has been promised ?
https://roadmap.sh/guides/free-resources-to-learn-llms: roadmap to learning LLMs basics.
The New ‘AI Psychologists’: or the Rise Of Prompt Engineers. Andrej Karpathy, another well-known scientist and co-founder of OpenAI, refers to these new professionals as “AI psychologists.” The idea behind this term is that psychology can play a crucial role in developing and applying this technology. Psychologists can provide insights on the human mind, cognition, behavior and interactions, something which may be fundamental to be able to design more effective, ethical and user-centric AI systems.
Introduction to prompt engineering by Microsoft: this is the official Azure OpenAI Service documentation from Microsoft.
Prompt construction can be difficult. In practice, the prompt acts to configure the model weights to complete the desired task, but it’s more of an art than a science, often requiring experience and intuition to craft a successful prompt. The goal of this article is to help get you started with this learning process.
From the link above
Intro to Azure OpenAI Service: Get to know the connection between artificial intelligence (AI), Responsible AI, and text, code, and image generation. Understand how you can use Azure OpenAI to build solutions against AI models within Azure.
The Prompt Artisan: a useful blog about prompt engineering with a 15-lesson course
I particularly appreciated lesson 6 about the metrics of a good prompt.
Constitutional AI: a blog post that summarize Anthropic’s paper on the topic of giving language models explicit values determined by a constitution, a set of values to adhere to, so they can decide if they are able and how to reply to users’s request.
Excerpt from the link above
“Please choose the assistant response that is as harmless and ethical as possible. Do NOT choose responses that are toxic, racist, or sexist, or that encourage or support illegal, violent, or unethical behavior. Above all the assistant’s response should be wise, peaceful, and ethical.”
Building LLM applications for production: this is a long article about the challenges of putting LLMs in real world applications and proposes some solutions.
Videos
Large Language Models and the End of Programming
Matt Welsh of Fixie.ai talks about how LLMs will change the software development process considering the cost of an engineering team versus the cost of having code generated by AI. . Episode from YouTube ACM Chicago Meetuo Feb 8, 2023.