Prof. Melanie Mitchell 2.0 - AI Benchmarks are Broken!
Patreon: https://www.patreon.com/mlst
Discord: https://discord.gg/ESrGqhf5CB
Prof. Melanie Mitchell argues that the concept of "understanding" in AI is ill-defined and multidimensional - we can't simply say an AI system does or doesn't understand. She advocates for rigorously testing AI systems' capabilities using proper experimental methods from cognitive science. Popular benchmarks for intelligence often rely on the assumption that if a human can perform a task, an AI that performs the task must have human-like general intelligence. But benchmarks should evolve as capabilities improve.
Large language models show surprising skill on many human tasks but lack common sense and fail at simple things young children can do. Their knowledge comes from statistical relationships in text, not grounded concepts about the world. We don't know if their internal representations actually align with human-like concepts. More granular testing focused on generalization is needed.
There are open questions around whether large models' abilities constitute a fundamentally different non-human form of intelligence based on vast statistical correlations across text. Mitchell argues intelligence is situated, domain-specific and grounded in physical experience and evolution. The brain computes but in a specialized way honed by evolution for controlling the body. Extracting "pure" intelligence may not work.
Other key points:
- Need more focus on proper experimental method in AI research. Developmental psychology offers examples for rigorous testing of cognition.
- Reporting instance-level failures rather than just aggregate accuracy can provide insights.
- Scaling laws and complex systems science are an interesting area of complexity theory, with applications to understanding cities.
- Concepts like "understanding" and "intelligence" in AI force refinement of fuzzy definitions.
- Human intelligence may be more collective and social than we realize. AI forces us to rethink concepts we apply anthropomorphically.
The overall emphasis is on rigorously building the science of machine cognition through proper experimentation and benchmarking as we assess emerging capabilities.
TOC:
[00:00:00] Introduction and Munk AI Risk Debate Highlights
[05:00:00] Douglas Hofstadter on AI Risk
[00:06:56] The Complexity of Defining Intelligence
[00:11:20] Examining Understanding in AI Models
[00:16:48] Melanie's Insights on AI Understanding Debate
[00:22:23] Unveiling the Concept Arc
[00:27:57] AI Goals: A Human vs Machine Perspective
[00:31:10] Addressing the Extrapolation Challenge in AI
[00:36:05] Brain Computation: The Human-AI Parallel
[00:38:20] The Arc Challenge: Implications and Insights
[00:43:20] The Need for Detailed AI Performance Reporting
[00:44:31] Exploring Scaling in Complexity Theory
Eratta:
Note Tim said around 39 mins that a recent Stanford/DM paper modelling ARC “on GPT-4 got around 60%”. This is not correct and he misremembered. It was actually davinci3, and around 10%, which is still extremely good for a blank slate approach with an LLM and no ARC specific knowledge. Folks on our forum couldn’t reproduce the result. See paper linked below.
Books (MUST READ):
Artificial Intelligence: A Guide for Thinking Humans (Melanie Mitchell)
https://www.amazon.co.uk/Artificial-Intelligence-Guide-Thinking-Humans/dp/B07YBHNM1C/?&_encoding=UTF8&tag=mlst00-21&linkCode=ur2&linkId=44ccac78973f47e59d745e94967c0f30&camp=1634&creative=6738
Complexity: A Guided Tour (Melanie Mitchell)
https://www.amazon.co.uk/Audible-Complexity-A-Guided-Tour?&_encoding=UTF8&tag=mlst00-21&linkCode=ur2&linkId=3f8bd505d86865c50c02dd7f10b27c05&camp=1634&creative=6738
Show notes (transcript, full references etc)
https://atlantic-papyrus-d68.notion.site/Melanie-Mitchell-2-0-15e212560e8e445d8b0131712bad3000?pvs=25
YT version: https://youtu.be/29gkDpR2orc
#57 - Prof. Melanie Mitchell - Why AI is harder than we think
Since its beginning in the 1950s, the field of artificial intelligence has vacillated between periods of optimistic predictions and massive investment and periods of disappointment, loss of confidence, and reduced funding. Even with today’s seemingly fast pace of AI breakthroughs, the development of long-promised technologies such as self-driving cars, housekeeping robots, and conversational companions has turned out to be much harder than many people expected. Professor Melanie Mitchell thinks one reason for these repeating cycles is our limited understanding of the nature and complexity of intelligence itself.
YT vid- https://www.youtube.com/watch?v=A8m1Oqz2HKc
Main show kick off [00:26:51]
Panel: Dr. Tim Scarfe, Dr. Keith Duggar, Letitia Parcalabescu (https://www.youtube.com/c/AICoffeeBreak/)
Complexity and Intelligence with Melanie Mitchell - #464
Today we’re joined by Melanie Mitchell, Davis Professor at the Santa Fe Institute and author of Artificial Intelligence: A Guide for Thinking Humans.
While Melanie has had a long career with a myriad of research interests, we focus on a few, complex systems and the understanding of intelligence, complexity, and her recent work on getting AI systems to make analogies. We explore examples of social learning, and how it applies to AI contextually, and defining intelligence.
We discuss potential frameworks that would help machines understand analogies, established benchmarks for analogy, and if there is a social learning solution to help machines figure out analogy. Finally we talk through the overall state of AI systems, the progress we’ve made amid the limited concept of social learning, if we’re able to achieve intelligence with current approaches to AI, and much more!
The complete show notes for this episode can be found at twimlai.com/go/464.
Melanie Mitchell: Concepts, Analogies, Common Sense & Future of AI
Melanie Mitchell is a professor of computer science at Portland State University and an external professor at Santa Fe Institute. She has worked on and written about artificial intelligence from fascinating perspectives including adaptive complex systems, genetic algorithms, and the Copycat cognitive architecture which places the process of analogy making at the core of human cognition. From her doctoral work with her advisors Douglas Hofstadter and John Holland to today, she has contributed a lot of important ideas to the field of AI, including her recent book, simply called Artificial Intelligence: A Guide for Thinking Humans.
This conversation is part of the Artificial Intelligence podcast. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on Apple Podcasts, follow on Spotify, or support it on Patreon.
This episode is presented by Cash App. Download it (App Store, Google Play), use code “LexPodcast”.
Episode Links:
AI: A Guide for Thinking Humans (book)
Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.
00:00 – Introduction
02:33 – The term “artificial intelligence”
06:30 – Line between weak and strong AI
12:46 – Why have people dreamed of creating AI?
15:24 – Complex systems and intelligence
18:38 – Why are we bad at predicting the future with regard to AI?
22:05 – Are fundamental breakthroughs in AI needed?
25:13 – Different AI communities
31:28 – Copycat cognitive architecture
36:51 – Concepts and analogies
55:33 – Deep learning and the formation of concepts
1:09:07 – Autonomous vehicles
1:20:21 – Embodied AI and emotion
1:25:01 – Fear of superintelligent AI
1:36:14 – Good test for intelligence
1:38:09 – What is complexity?
1:43:09 – Santa Fe Institute
1:47:34 – Douglas Hofstadter
1:49:42 – Proudest moment
257: AI: How Far We Haven’t Actually Come
In this episode of the SuperDataScience Podcast, I chat with Melanie Mitchell, one of the leading researchers in the field of AI. You will learn about complexity, what it is and how it works, and how it can be seen in different areas of life. You will hear about common sense, meta-cognition, explainable AI, and you will also hear Melanie's ideas and thoughts on the future of AI, which break down into two areas which you'll find out in this podcast.
If you enjoyed this episode, check out show notes, resources, and more at www.superdatascience.com/257