The speaker prefers simple code and constantly works on simplifying everything, although they acknowledge investing extra effort in making prompts work with lower models. They believe the effort is not wasted because a better prompt can improve the performance of better models as well. The speaker consciously considers the amount of time spent on problems that may not need solving eventually. They gave an example of dropping efforts on OCR when GPT4B was anticipated, indicating a strategy of anticipating future models to optimize their work.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode