AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
ChatGPT Training, Superintelligence, & AI Funding in Vector Databases | E12
This Day in AI Podcast
The Negative Bias Behavior of Chatbots
The paper says that if a model shows across many tasks that it acts in a very selfish manner, then engineers could possibly think about retraining or fine tuning it to ease its aberrant behavior. But the thing is, as I said earlier, not every person training these models is going to be benevolent. And the people who want to do bad things can induce that megalomania behavior by making the thing anxious.
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