Chat ML has been announced as a tool that can be used to test content filters. How much of the stuff that you are seeing, do you think is effectively caught by those content filters such that it's not required in practice? I don't know if they're catching things, or if their content filter is just like highlighting the outputs once they've been created. There's a few interesting points there though. If you stop the generation before it finishes, it seems like it won't then be caught in the content filter. You can have like malicious output, but if you stop it before it reaches the end, it won't highlight it in orange.

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