Waiting times for GPT four are typically over a minute, sometimes over 90 seconds, but the results are good. By adding a chain of thought element to GPT four, even if it doesn't visibly improve the quality, the fine-tuning process becomes faster and more efficient. This showcases the potential shift towards using synthetic data in training models, which can help mitigate issues like exposure to toxic and hateful content. By reducing the amount of undesirable data, the models can perform better without the need for extensive post-processing.

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