Is Artificial Superintelligence Imminent? with Tim Rocktäschel - #706
Today, we're joined by Tim Rocktäschel, senior staff research scientist at Google DeepMind, professor of Artificial Intelligence at University College London, and author of the recently published popular science book, “Artificial Intelligence: 10 Things You Should Know.” We dig into the attainability of artificial superintelligence and the path to achieving generalized superhuman capabilities across multiple domains. We discuss the importance of open-endedness in developing autonomous and self-improving systems, as well as the role of evolutionary approaches and algorithms. Additionally, we cover Tim’s recent research projects such as “Promptbreeder,” “Debating with More Persuasive LLMs Leads to More Truthful Answers,” and more.
The complete show notes for this episode can be found at https://twimlai.com/go/706.
Open-Ended AI: The Key to Superhuman Intelligence? - Prof. Tim Rocktäschel
Prof. Tim Rocktäschel, AI researcher at UCL and Google DeepMind, talks about open-ended AI systems. These systems aim to keep learning and improving on their own, like evolution does in nature.
Ad: Are you a hardcore ML engineer who wants to work for Daniel Cahn at SlingshotAI building AI for mental health? Give him an email! - danielc@slingshot.xyz
TOC:
00:00:00 Introduction to Open-Ended AI and Key Concepts
00:01:37 Tim Rocktäschel's Background and Research Focus
00:06:25 Defining Open-Endedness in AI Systems
00:10:39 Subjective Nature of Interestingness and Learnability
00:16:22 Open-Endedness in Practice: Examples and Limitations
00:17:50 Assessing Novelty in Open-ended AI Systems
00:20:05 Adversarial Attacks and AI Robustness
00:24:05 Rainbow Teaming and LLM Safety
00:25:48 Open-ended Research Approaches in AI
00:29:05 Balancing Long-term Vision and Exploration in AI Research
00:37:25 LLMs in Program Synthesis and Open-Ended Learning
00:37:55 Transition from Human-Based to Novel AI Strategies
00:39:00 Expanding Context Windows and Prompt Evolution
00:40:17 AI Intelligibility and Human-AI Interfaces
00:46:04 Self-Improvement and Evolution in AI Systems
Show notes (New!) https://www.dropbox.com/scl/fi/5avpsyz8jbn4j1az7kevs/TimR.pdf?rlkey=pqjlcqbtm3undp4udtgfmie8n&st=x50u1d1m&dl=0
REFS:
00:01:47 - UCL DARK Lab (Rocktäschel) - AI research lab focusing on RL and open-ended learning - https://ucldark.com/
00:02:31 - GENIE (Bruce) - Generative interactive environment from unlabelled videos - https://arxiv.org/abs/2402.15391
00:02:42 - Promptbreeder (Fernando) - Self-referential LLM prompt evolution - https://arxiv.org/abs/2309.16797
00:03:05 - Picbreeder (Secretan) - Collaborative online image evolution - https://dl.acm.org/doi/10.1145/1357054.1357328
00:03:14 - Why Greatness Cannot Be Planned (Stanley) - Book on open-ended exploration - https://www.amazon.com/Why-Greatness-Cannot-Planned-Objective/dp/3319155237
00:04:36 - NetHack Learning Environment (Küttler) - RL research in procedurally generated game - https://arxiv.org/abs/2006.13760
00:07:35 - Open-ended learning (Clune) - AI systems for continual learning and adaptation - https://arxiv.org/abs/1905.10985
00:07:35 - OMNI (Zhang) - LLMs modeling human interestingness for exploration - https://arxiv.org/abs/2306.01711
00:10:42 - Observer theory (Wolfram) - Computationally bounded observers in complex systems - https://writings.stephenwolfram.com/2023/12/observer-theory/
00:15:25 - Human-Timescale Adaptation (Rocktäschel) - RL agent adapting to novel 3D tasks - https://arxiv.org/abs/2301.07608
00:16:15 - Open-Endedness for AGI (Hughes) - Importance of open-ended learning for AGI - https://arxiv.org/abs/2406.04268
00:16:35 - POET algorithm (Wang) - Open-ended approach to generate and solve challenges - https://arxiv.org/abs/1901.01753
00:17:20 - AlphaGo (Silver) - AI mastering the game of Go - https://deepmind.google/technologies/alphago/
00:20:35 - Adversarial Go attacks (Dennis) - Exploiting weaknesses in Go AI systems - https://www.ifaamas.org/Proceedings/aamas2024/pdfs/p1630.pdf
00:22:00 - Levels of AGI (Morris) - Framework for categorizing AGI progress - https://arxiv.org/abs/2311.02462
00:24:30 - Rainbow Teaming (Samvelyan) - LLM-based adversarial prompt generation - https://arxiv.org/abs/2402.16822
00:25:50 - Why Greatness Cannot Be Planned (Stanley) - 'False compass' and 'stepping stone collection' concepts - https://www.amazon.com/Why-Greatness-Cannot-Planned-Objective/dp/3319155237
00:27:45 - AI Debate (Khan) - Improving LLM truthfulness through debate - https://proceedings.mlr.press/v235/khan24a.html
00:29:40 - Gemini (Google DeepMind) - Advanced multimodal AI model - https://deepmind.google/technologies/gemini/
00:30:15 - How to Take Smart Notes (Ahrens) - Effective note-taking methodology - https://www.amazon.com/How-Take-Smart-Notes-Nonfiction/dp/1542866502
(truncated, see shownotes)
Advancing Deep Reinforcement Learning with NetHack, w/ Tim Rocktäschel - #527
Take our survey at twimlai.com/survey21!
Today we’re joined by Tim Rocktäschel, a research scientist at Facebook AI Research and an associate professor at University College London (UCL).
Tim’s work focuses on training RL agents in simulated environments, with the goal of these agents being able to generalize to novel situations. Typically, this is done in environments like OpenAI Gym, MuJuCo, or even using Atari games, but these all come with constraints. In Tim’s approach, he utilizes a game called NetHack, which is much more rich and complex than the aforementioned environments.
In our conversation with Tim, we explore the ins and outs of using NetHack as a training environment, including how much control a user has when generating each individual game and the challenges he's faced when deploying the agents. We also discuss his work on MiniHack, an environment creation framework and suite of tasks that are based on NetHack, and future directions for this research.
The complete show notes for this episode can be found at twimlai.com/go/527.
Tim & Heinrich — Democraticizing Reinforcement Learning Research
Since reinforcement learning requires hefty compute resources, it can be tough to keep up without a serious budget of your own. Find out how the team at Facebook AI Research (FAIR) is looking to increase access and level the playing field with the help of NetHack, an archaic rogue-like video game from the late 80s.
Links discussed:
The NetHack Learning Environment:
https://ai.facebook.com/blog/nethack-learning-environment-to-advance-deep-reinforcement-learning/
Reinforcement learning, intrinsic motivation:
https://arxiv.org/abs/2002.12292
Knowledge transfer:
https://arxiv.org/abs/1910.08210
Tim Rocktäschel is a Research Scientist at Facebook AI Research (FAIR) London and a Lecturer in the Department of Computer Science at University College London (UCL). At UCL, he is a member of the UCL Centre for Artificial Intelligence and the UCL Natural Language Processing group. Prior to that, he was a Postdoctoral Researcher in the Whiteson Research Lab, a Stipendiary Lecturer in Computer Science at Hertford College, and a Junior Research Fellow in Computer Science at Jesus College, at the University of Oxford.
https://twitter.com/_rockt
Heinrich Kuttler is an AI and machine learning researcher at Facebook AI Research (FAIR) and before that was a research engineer and team lead at DeepMind.
https://twitter.com/HeinrichKuttler
https://www.linkedin.com/in/heinrich-kuttler/
Topics covered:
0:00 a lack of reproducibility in RL
1:05 What is NetHack and how did the idea come to be?
5:46 RL in Go vs NetHack
11:04 performance of vanilla agents, what do you optimize for
18:36 transferring domain knowledge, source diving
22:27 human vs machines intrinsic learning
28:19 ICLR paper - exploration and RL strategies
35:48 the future of reinforcement learning
43:18 going from supervised to reinforcement learning
45:07 reproducibility in RL
50:05 most underrated aspect of ML, biggest challenges?
Get our podcast on these other platforms:
Apple Podcasts: http://wandb.me/apple-podcasts
Spotify: http://wandb.me/spotify
Google: http://wandb.me/google-podcasts
YouTube: http://wandb.me/youtube
Soundcloud: http://wandb.me/soundcloud
Tune in to our bi-weekly virtual salon and listen to industry leaders and researchers in machine learning share their research:
http://wandb.me/salon
Join our community of ML practitioners where we host AMA's, share interesting projects and meet other people working in Deep Learning:
http://wandb.me/slack
Our gallery features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, and industry leaders sharing best practices:
https://wandb.ai/gallery