Alignment
16 videos • 21 views • by Tunadorable
1
have benchmarks been the problem the whole time?!?
Tunadorable
Download
2
Open-Endedness is Essential for Artificial Superhuman Intelligence
Tunadorable
Download
3
What is Direct Preference Optimization?
Tunadorable
Download
4
Hallucination in Language Models is NEVER Going Away
Tunadorable
Download
5
Creating a Training Dataset for Conscious AI
Tunadorable
Download
6
Why Evolution Favors AI Over Humans (Paper Breakdown)
Tunadorable
Download
7
Aligning LLMs with Diverse Moralities
Tunadorable
Download
8
Conversational Swarm Intelligence (Paper Breakdown)
Tunadorable
Download
9
Discovering Moral Dimensions in ChatGPT (paper breakdown)
Tunadorable
Download
10
The Impossibility and Uncertainy of AGI Alignment (Paper Breakdown)
Tunadorable
Download
11
Are proofs the only guaranteed way to prevent AGI apocalypse????? (Paper Breakdown)
Tunadorable
Download
12
AGI Alignment is DOOMED - Symbiosis Instead (Paper Breakdown)
Tunadorable
Download
13
An Economic Model of AGI Symbiotic Interdependence
Tunadorable
Download
14
The Circus of AI Alignment Approaches That Won't Work
Tunadorable
Download
15
Heuristic Imperatives & the GATO Framework (Detailed breakdown & my opinions)
Tunadorable
Download
16
How do we Trust and Control AI? (Paper Breakdown)
Tunadorable
Download