Evidence receipt / belief
Published · transcript-backedDwarkesh Patel: belief
11 Jun 2024 Dwarkesh Podcast Francois Chollet — Why the biggest AI models can't solve simple puzzles
“How many of them are not 11, 12, or 13 years old? I agree this is not rocket science.”
Source trail
Everything needed to verify it.
- Speaker
- Dwarkesh Patel
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 11 Jun 2024
- Publisher
- Dwarkesh Podcast
Transcript context
…Sure, that's a memorization benchmark. Let's talk about what that means. Here's one question from that benchmark: "30 students are in a class. One-fifth of them are 12-year-olds, One-third are 13-year-olds, One-tenth are 11-year-olds. How many of them are not 11, 12, or 13 years old? I agree this is not rocket science. You can write down on paper how you go through this problem. A smart high school kid should be able to solve it. About memorization, it still has to reason through how to think about fractions, the context of the whole problem, and then combine different calculations to write the final answer. It depends on how you want to define reasoning. There are two definitions you can use. One is, I have available a set of program templates. It’s the structure of the puzzle, which can also generate its solution. I'm going to identify the right template, which is in my memory, input the new values into the template, run the program, and get the solution. You could say this is reasoning. I say, “yeah sure, okay.” Here’s another definition of reasoning. When you're faced with a puzzle and you don't already have a program in memory to solve it, it’s the ability to synthesize on the fly a new program based on bits and pieces of existing programs that you have. You have to do on-the-fly program synthesis. That's actually dramatically harder than just fetching the right memorized program and reapplying it.…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.