We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
back
Open-Ended AI: The Key to Superhuman Intelligence? - Prof. Tim Rocktäschel
55:10
Share
2024/10/4
Machine Learning Street Talk (MLST)
AI Chapters
Transcribe
Chapters
What is Open-Ended AI and Why Does It Matter?
Tim Rocktäschel's Journey in AI Research
Defining Open-Endedness in AI Systems
The Subjective Nature of Interestingness and Learnability
Practical Examples and Limitations of Open-Ended AI
How Do We Assess Novelty in Open-Ended AI Systems?
Adversarial Attacks and the Robustness of AI
Rainbow Teaming: Enhancing LLM Safety
Exploring Open-Ended Research Approaches in AI
Balancing Long-term Vision and Exploration in AI Research
LLMs in Program Synthesis and Open-Ended Learning
Expanding Context Windows and Evolving Prompts
AI Intelligibility and Human-AI Interfaces
Self-Improvement and Evolution in AI Systems
Shownotes
Transcript
No transcript made for this episode yet, you may request it for free.