Evolving AI Architectures and Future Directions

This chapter explores the advancements in AI architectures, particularly the CAN model, and its relevance to scientific applications. It discusses the challenges of interpretability, hybrid models, and the evolution of language models, emphasizing the need for empirical benchmarks to guide future improvements in AI.

Transcript

chevron_right

Play full episode

chevron_right

Transcript

Episode notes

In this episode of The Cognitive Revolution, Nathan explores the cutting-edge intersection of AI and biology with Stanford assistant professor Brian Hie. Discover how AI is revolutionizing our understanding of biological systems and creating new possibilities for interventions. Brian discusses his groundbreaking papers on hybrid AI architectures, the surprising capabilities of language models trained on DNA sequences, and AI-guided evolution of antibodies. Join us for an insightful journey into the future of AI in biology, touching on biosecurity, drug discovery, and the challenges of interpreting AI models in biological contexts.

Links :

Brian Hie : https://x.com/BrianHie

Scanorama paper

Mechanistic Design and Scaling of Hybrid Architectures

Sequence modeling and design from molecular to genome scale with Evo

Unsupervised evolution of protein and antibody complexes with a structure-informed language model

Apply to join over 400 Founders and Execs in the Turpentine Network: https://www.turpentinenetwork.co/

SPONSORS:

80,000 Hours: 80,000 Hours offers free one-on-one career advising for Cognitive Revolution listeners aiming to tackle global challenges, especially in AI. They connect high-potential individuals with experts, opportunities, and personalized career plans to maximize positive impact. Apply for a free call at https://80000hours.org/cognitiverevolution to accelerate your career and contribute to solving pressing AI-related issues.

Brave: The Brave search API can be used to assemble a data set to train your AI models and help with retrieval augmentation at the time of inference. All while remaining affordable with developer first pricing, integrating the Brave search API into your workflow translates to more ethical data sourcing and more human representative data sets. Try the Brave search API for free for up to 2000 queries per month at https://bit.ly/BraveTCR

Omneky: Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that actually work customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off https://www.omneky.com/

Oracle: Oracle Cloud Infrastructure (OCI) is a single platform for your infrastructure, database, application development, and AI needs. OCI has four to eight times the bandwidth of other clouds; offers one consistent price, and nobody does data better than Oracle. If you want to do more and spend less, take a free test drive of OCI at https://oracle.com/cognitive

RECOMMENDED PODCAST:

This Won't Last - Eavesdrop on Keith Rabois, Kevin Ryan, Logan Bartlett, and Zach Weinberg's monthly backchannel ft their hottest takes on the future of tech, business, and venture capital.

Spotify: https://open.spotify.com/show/2HwSNeVLL1MXy0RjFPyOSz

CHAPTERS:

(00:00:00) About the Show

(00:00:22) About the Episode

(00:03:22) Introduction and Overview

(00:03:55) AI for Biology: Big Picture

(00:05:49) Challenges in Biology and Drug Discovery

(00:08:36) Scanorama and Single Cell Transcriptomics

(00:10:27) Brian's Research Identity

(00:13:00) Mechanistic Design of Hybrid Architectures

(00:14:52) Evo: DNA Language Model (Part 1)

(00:18:10) Sponsors: 80,000 Hours | Brave