Training open source models with specific techniques to improve performance can inadvertently erase safety behaviors. Improving performance can lead to the unintentional removal of safety mechanisms from AI systems. This poses challenges in controlling the behavior of advanced AI models like GPT-4 and others, making it crucial to strike a balance between performance enhancements and maintaining safety features to effectively use the technology.

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