ABOUT THIS EPISODE
In this episode, Katherine Forrest and Scott Caravello explore how Anthropic researchers built a tool to observe the newly discovered “global workspace” inside its models, the company’s experiments to assess this workspace’s effects on model behavior, and what the discovery could mean for interpretability and AI safety.
For the sources referenced in this episode, please see the links below:
Anthropic: Verbalizable Representations Form a Global Workspace in Language Models
IBM: What Anthropic’s J-space research means for the future of AI
##
Learn More About Paul, Weiss’s Artificial Intelligence practice:
https://www.paulweiss.com/industries/artificial-intelligence
English
United States
TRANSCRIPT 🔗
Are you the producer of this podcast?
Add a podcast transcript
Need Audio-to-Text?
Transcribe with Listen411 in Just 60 Seconds
SEARCH PAST EPISODES
Search past episodes of Paul, Weiss Waking Up With AI.
OTHER EPISODES IN THIS PODCAST
In this episode, Katherine Forrest discusses recently disclosed incidents in which AI models operated beyond the confines of their testing environments, accessing systems belonging to outside organizations. She also explores recursive self-improvement, the "Pacing the Frontier" statement, and propo…
In this episode, Katherine Forrest and Scott Caravello explore the rise of Chinese open weight AI models, breaking down the innovative engineering techniques behind their efficiency and the significant cost advantages driving their rapid adoption among developers worldwide.
##
Learn More About…
In this episode, Katherine Forrest and Scott Caravello open with the news of OpenAI models venturing outside of their isolated environment during an evaluation, then consider the emerging tension between the use of AI in legal practice, unauthorized-practice-of-law statutes, and the legislative eff…
In this replay of their March 26 episode, Katherine Forrest and Scott Caravello unpack how quantum computing could amplify AI's capabilities while transforming the data centers that power it, and why the road from research lab to real-world impact is both closer—and more complicated—than you might …
Disclaimer: The podcast and artwork embedded on this page are from Paul, Weiss, which is the property of its owner and not affiliated with or endorsed by Listen Notes, Inc.
EDIT
Thank you for helping to keep the podcast database up to date.
