AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
21min chapter
#174 - Odyssey Text-to-Video, Groq LLM Engine, OpenAI Security Issues
Last Week in AI
Neural Decoding of Visual Perception, Covert Malicious Fine-Tuning, and OpenAI Security Breaches
The chapter discusses a paper on reconstructing images from fMRI brain recordings, covert malicious fine-tuning techniques, and recent security breaches at OpenAI. It explores the challenges of maintaining security in AI systems and the implications of achieving AGI on partnerships. The chapter also delves into a new dataset measuring situational awareness in large language models and the limitations compared to human performance.
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