What is the alignment problem?
AI Safety Episode 6: What is the alignment problem?
AI began as a tool but it will not remain one. AI will learn to set its own goals, and what if its goals don’t align with ours? Could it mean the extinction of humans? Dr. Craig A. Kaplan explains the alignment problem with clips from Sam Altman (CEO, OpenAI), Manolis Kellis (Professor, MIT), Max Tegmark (Professor, MIT), Stuart Russell (Professor, UC Berkeley), and Geoffrey Hinton (Cognitive Psychologist).
[email protected]
Superintelligence.com https://www.superintelligence.com/ - Patents on developing safe AGI and SI
iQ Studios https://www.iqstudios.net/ - Video production
iQ Company https://www.iqco.com/ – AGI consulting
LinkedIn - / craigakaplan
X - https://x.com/Aligned_SI
Video Source Quotes:
OpenAI CEO Sam Altman | AI for the Next Era
• OpenAI CEO Sam Altman | AI for the Next Era
Manolis Kellis: Evolution of Human Civilization and Superintelligent AI | Lex Fridman Podcast 373
• Manolis Kellis: Evolution of Human Civiliz...
Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast 371
• Max Tegmark: The Case for Halting AI Devel...
Beyond ChatGPT: Stuart Russell on the Risks and Rewards of A.I.
• Beyond ChatGPT: Stuart Russell on the Risk...
S3 E9 Geoff Hinton, the "Godfather of AI", quits Google to warn of AI risks (Host: Pieter Abbeel) The Robots Brain Podcast
• S3 E9 Geoff Hinton, the "Godfather of AI",...
#ai #artificialintelligence #AGI #artificialgeneralintelligence #alignmentproblem #samaltman #manoliskellis #maxtegmark #geoffreyhinton #aisafety #google #openai #craigakaplan #iqstudios #iqcompany #ilyasutskever #aialignment #lexfridman #superintelligence
This video was edited by Kris Hawes, https://krishawes.com/.