About this episode
In this episode, I share my hands-on experience with OpenAI’s GPT-5, the company’s new frontier model. As one of the first users outside of OpenAI to test the model, I put GPT-5 head-to-head with GPT-4.1 across real-world product use cases—from writing PRDs to generating code to assisting with visual design work. This is my unfiltered look at what GPT-5 can (and can’t) do—and how it changes the game for builders. What you’ll learn: 1. How GPT-5 differs from previous models with its engineering-focused approach to problem-solving and tendency to prioritize technical details over business context 2. A comparative analysis of how GPT-5 and GPT-4.1 generate different types of product requirement documents and prototypes for the same prompt 3. Why GPT-5 excels at technical writing, functional requirements, and code generation while potentially skipping important business discovery questions 4. The model’s impressive spatial awareness capabilities when generating images for interior design and other visual tasks 5. Practical considerations for choosing the right model based on your specific use case and audience 6. How GPT-5’s extensive tool-calling behavior and bullet-point communication style reflect its engineering-oriented design — Brought to you by ChatPRD —an AI copilot for PMs and their teams: https://www.chatprd.ai/howiai — 25k giveaway: To celebrate 25,000 YouTube followers, we’re doing a giveaway. Win a free year of my favorite AI products, including v0, Replit, Lovable, Bolt, Cursor, and, of course, ChatPRD, by leaving a rating and review on your favorite podcast app and subscribing to the podcast on YouTube. To enter: https://www.howiaipod.com/giveaway — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo — In this episode, we cover: (00:00) Introduction to GPT-5 (04:34) Testing GPT-5 in ChatPRD for document generation (07:10) Comparing GPT-5 and GPT-4.1 on business vs. technical orientation (11:22) Side-by-side comparison of PRDs generated by both models (15:23) Where GPT-5 excels: Technical considerations and documentation quality (17:35) Comparing prototypes generated from different model outputs (19:57) Testing homepage critique capabilities between models (23:14) OpenAI’s strengths in API design and developer support (25:37) GPT-5’s performance as a coding assistant (27:26) Examining GPT-5 in ChatGPT’s interface (28:50) Testing GPT-5’s front-end design capabilities (31:17) Personal use case: bathroom remodel planning (33:45) Comparing GPT-5 vs. GPT-4 for interior design visualization (38:10) Summary of key findings and recommendations — Tools referenced: • OpenAI: https://openai.com/ • ChatGPT: https://chat.openai.com/ • Claude: https://claude.ai/ • Gemini: https://gemini.google.com/ • Cursor: https://cursor.sh/ • v0: https://v0.dev/ • Lovable: https://lovable.dev/ • Bolt: https://bolt.com/ • LaunchDarkly AI Configs: https://launchdarkly.com/docs/home/ai-configs — Other reference: • Benjamin Moore paints: https://www.benjaminmoore.com/ — Production and marketing by https://penname.co/ . For inquiries about sponsoring the podcast, email jordan@penname.co.