The first principles it writes are that AI is just a tool, AI is powerful, AI is not conscious. The tactic they suggest is instructing the model to work out its own solution before rushing to a conclusion. They also point to the example of using code execution to perform more accurate calculations or call external API's. And this kind of gets back to how they're now open sourcing evaluation models so that people can get more involved in helping them improve chat CPT over time.

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