I've tried asking just about every code gen AI to write me a denial of service script. Results vary. Do you have a standard process that is specifically dedicated to, you know, avoiding harmful code? Is there a sort of standard battery of tests that you measure these sorts of things against? LAMA2 has been released and it's heavily RLHF, as you might have seen yourself from the demos. I believe a lot will be also discovered there in terms of behaviors that are aligned with how we expect the models to behave.

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