EPISODE · Aug 10, 2025 · 40 MIN
Episode 1: GPT-5, Opus 4.1, GPT-OSS-2B, and more!
from Ship AI · host Manav Gupta
In this first episode, Manav Gupta and Mihai Criveti put the latest AI models through their paces in a head-to-head coding challenge. Watch as Claude Opus 4.1, GPT-5, and the open-source GPT OSS 20 billion compete to build interactive games and applications from simple prompts.Highlights:Live coding challenges including Snake, Minesweeper, and a Prince of Persia cloneReal-time comparison of how each model handles game development, from basic functionality to "kawaii" stylingTesting complex technical tasks like creating IBM mainframe architecture diagramsClassic AI benchmark tests (counting letters, arithmetic problems) with surprising resultsMihai runs GPT OSS locally on his own GPU, showcasing impressive open-source capabilitiesKey Takeaways:Claude Opus 4.1 emerges as the overall winner with cleaner interfaces and superior artifact managementGPT-5 shows promise but struggles with canvas implementationOpen-source models are rapidly closing the gap with commercial offeringsDiscussion on how these tools are reshaping the future of software development
What this episode covers
In this first episode, Manav Gupta and Mihai Criveti put the latest AI models through their paces in a head-to-head coding challenge. Watch as Claude Opus 4.1, GPT-5, and the open-source GPT OSS 20 billion compete to build interactive games and applications from simple prompts.Highlights:Live coding challenges including Snake, Minesweeper, and a Prince of Persia cloneReal-time comparison of how each model handles game development, from basic functionality to "kawaii" stylingTesting complex technical tasks like creating IBM mainframe architecture diagramsClassic AI benchmark tests (counting letters, arithmetic problems) with surprising resultsMihai runs GPT OSS locally on his own GPU, showcasing impressive open-source capabilitiesKey Takeaways:Claude Opus 4.1 emerges as the overall winner with cleaner interfaces and superior artifact managementGPT-5 shows promise but struggles with canvas implementationOpen-source models are rapidly closing the gap with commercial offeringsDiscussion on how these tools are reshaping the future of software development
NOW PLAYING
Episode 1: GPT-5, Opus 4.1, GPT-OSS-2B, and more!
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.