Multimodal by Bakz T. Future cover image

Multimodal by Bakz T. Future

#48 - The Art of Prompt Engineering with Andrew Mayne (ex-OpenAI Creative Apps and Science Communicator)

Dec 6, 2023
Andrew Mayne, ex-OpenAI Creative Apps and Science Communicator, discusses prompt engineering, early days at OpenAI, challenges of promoting GPT-3, DALL-E 3, prompt design changes, and fine-tuning ChatGPT to mimic personalities. They also explore the potential of GPT-4 Vision and multi-modality, AI-generated books, jail breaks as gimmicky achievements, AI models in stock market analysis, making reliable chatbots, and the power of technology and teaching.
03:12:08

Episode guests

Podcast summary created with Snipd AI

Quick takeaways

  • Prompting techniques have evolved to optimize for instruction and generate more reliable responses.
  • Models go through different stages of training, including fine-tuning and post-training optimization, to enhance performance and reliability.

Deep dives

Enhanced Prompting Techniques

Prompting techniques have evolved to optimize for instruction and generate more reliable responses. The introduction of instruct models allows for a more user-friendly experience, reducing the mental effort required to craft prompts. The focus has shifted from leading the model with complex prompts to simple and clear instructions, enabling users to get desired outputs with ease.

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner