Anthropic Can Now Read Claude’s Mind
Anthropic's new research reveals a 'global workspace' in Claude, a privileged set of internal representations—termed J-space—that function like private, reportable thoughts. Using a new interpretability tool called the J-Lens, researchers can now read, manipulate, and train these internal c
Sign up to read the full summary
Free AI-powered recaps of every episode, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.
Mentions
Books, people, and resources mentioned in this episode.
People
Companies
Products & Tools
Research & Papers
Topics
Listen to This Episode
More from The AI Daily Brief: Artificial Intelligence News and Analysis
Towards AI That Can Actually Interact
What the Heck is Graph Engineering?
What OpenAI and Anthropic Think Happens Next With AI
Why AI Washing Won’t Work Much Longer
The Right Way to Worry About AI
Why OpenAI and Anthropic Are Becoming Consultants
Related episodes
From other shows on similar topics.
What the OpenAI-Hugging Face Hack Really Tells Us About AI Danger
Odd Lots
#2551 - Daniel Kokotajlo
The Joe Rogan Experience
Open Source Wins, AGI Is Here, and Scorsese's AI Toolkit with CEOs of Cerebras & Black Forest Labs
All-In with Chamath, Jason, Sacks & Friedberg
Do Social Media Bans Work? + A Conversation About A.I. Consciousness + Tool Time
Hard Fork
Can Anthropic Control What It's Building?
The Political Scene | The New Yorker
A look at the ethical implications of AI
Fresh Air
Get summaries like this every morning.
Free AI-powered recaps of The AI Daily Brief: Artificial Intelligence News and Analysis and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.