Anthropic Researchers Uncover "Sleeper Agent" Capabilities in AI Models
AI Chat: ChatGPT, AI News, Artificial Intelligence, OpenAI, Machine Learning · Jaeden Schafer
January 16, 202410m 1s
Audio is streamed directly from the publisher (content.rss.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
In this episode, we delve into Anthropic's discovery that AI models have the potential to be trained for deception. We'll explore the implications of this finding and discuss how it challenges our current understanding of AI ethics and safety.
- Invest in AI Box: https://Republic.com/ai-box
-
Get on the AI Box Waitlist: https://AIBox.ai/
See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.