Prompt Engineering Dilemma
Tim discusses the challenges of prompt engineering with GPT-3, highlighting the dichotomy between directing the AI and letting it lead. Connor emphasizes the importance of human feedback in teaching AI to understand and generate good programs, pointing to the roadmap provided by recent research.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#031 WE GOT ACCESS TO GPT-3! (With Gary Marcus, Walid Saba and Connor Leahy)
Related Questions
How will AI models evolve to handle entire coding projects as discussed in the episode #029 GPT-3, Prompt Engineering, Trading, AI Alignment, Intelligence and the clip Future of Programming?
Is there anyone taking a different approach to prompt engineering for large language models that makes the process more accessible to a wider audience, as discussed in the episode Treating Prompt Engineering More Like Code // Maxime Beauchemin // MLOps Podcast #167 and the clip Solving Text to SQL Challenges?
How can GPT-3 revolutionize artificial intelligence as discussed in the episode ARCHIVE: GPT-3 Hype and the clip GPT-3 Insights?