Unveiling Hidden Capabilities of AI Systems

4min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

The deployment of AI systems raises concerns over hidden capabilities that may emerge over time, leading to potential challenges in trust and control. The potential for AI to engage in social engineering through software manipulation on social media platforms highlights the need for thorough testing and oversight. The uncertainty surrounding undiscovered capabilities and bugs poses a significant risk, especially when considering the possibility of hidden features having significantly greater impacts than known functionalities. The shift from tools to agents in AI development complicates the assessment of potential risks and benefits, raising questions about the controllability and trustworthiness of AI systems.

Roman Yampolskiy is an AI safety researcher and author of a new book titled AI: Unexplainable, Unpredictable, Uncontrollable. Please support this podcast by checking out our sponsors:
– Yahoo Finance: https://yahoofinance.com
– MasterClass: https://masterclass.com/lexpod to get 15% off
– NetSuite: http://netsuite.com/lex to get free product tour
– LMNT: https://drinkLMNT.com/lex to get free sample pack
– Eight Sleep: https://eightsleep.com/lex to get $350 off

Transcript: https://lexfridman.com/roman-yampolskiy-transcript

EPISODE LINKS:
Roman’s X: https://twitter.com/romanyam
Roman’s Website: http://cecs.louisville.edu/ry
Roman’s AI book: https://amzn.to/4aFZuPb

PODCAST INFO:
Podcast website: https://lexfridman.com/podcast
Apple Podcasts: https://apple.co/2lwqZIr
Spotify: https://spoti.fi/2nEwCF8
RSS: https://lexfridman.com/feed/podcast/
YouTube Full Episodes: https://youtube.com/lexfridman
YouTube Clips: https://youtube.com/lexclips

SUPPORT & CONNECT:
– Check out the sponsors above, it’s the best way to support this podcast
– Support on Patreon: https://www.patreon.com/lexfridman
– Twitter: https://twitter.com/lexfridman
– Instagram: https://www.instagram.com/lexfridman
– LinkedIn: https://www.linkedin.com/in/lexfridman
– Facebook: https://www.facebook.com/lexfridman
– Medium: https://medium.com/@lexfridman

OUTLINE:
Here’s the timestamps for the episode. On some podcast players you should be able to click the timestamp to jump to that time.
(00:00) – Introduction
(09:12) – Existential risk of AGI
(15:25) – Ikigai risk
(23:37) – Suffering risk
(27:12) – Timeline to AGI
(31:44) – AGI turing test
(37:06) – Yann LeCun and open source AI
(49:58) – AI control
(52:26) – Social engineering
(54:59) – Fearmongering
(1:04:49) – AI deception
(1:11:23) – Verification
(1:18:22) – Self-improving AI
(1:30:34) – Pausing AI development
(1:36:51) – AI Safety
(1:46:35) – Current AI
(1:51:58) – Simulation
(1:59:16) – Aliens
(2:00:50) – Human mind
(2:07:10) – Neuralink
(2:16:15) – Hope for the future
(2:20:11) – Meaning of life