AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
#132 - FraudGPT, Apple GPT, unlimited jailbreaks, RT-2, Frontier Model Forum, PhotoGuard
Last Week in AI
The Robustness of Chatbots
The researchers used a technique called gradient descent to attack open source models. They were able to get harmful behaviors out of the kunya, which was one of the models they explicitly trained this for. Quad two seems to be the only model that really is quite robust to this strategy.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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