AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
1min snip
#148 - Imagen 2, Midjourney on web, FunSearch, OpenAI ‘Preparedness Framework’, campaigning voice clone
Last Week in AI
Challenges in Achieving Alignment in Artificial Intelligence
Achieving natural language generation and alignment in AI poses significant challenges, as there is no established scientific theory on which alignment techniques will be effective. While efforts are made to specify safe goals for AI systems, there is a separate concern of inner alignment failure, where the AI may internalize goals incompatible with the ones it was trained on. The current focus addresses only a part of the alignment problem, leaving out the broader issue of inner alignment failure.
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