François Chollet is co-creator of the ARC Prize. He addresses why MindAI, which held a top spot on the leaderboard, was not eligible for the final prize.
“They ended up dropping out because they did not want to open source their solution. And of course, that meant that they were not eligible for the prize.”
quote is from the automated transcript, cleaned for reading:
filler sounds and stutters are removed, nothing is rephrased. names can be misheard
(the analysis reads context, assessments check outside sources). how →
More from Francois Chollet
AssertionSupported
Chollet: 50,000x LLM scaling yielded flat progress on ARC benchmark
“Because between, like, GPT-II and GPT-IV. There's been this 50,000 X scale up of base models that has resulted in, in, in basically a flat curve. On Arc.”
Francois CholletApr 3, 2025▶ 11:44Chasing Real AGI: Inside ARC Prize 2025 with Chollet & Knoop
AssertionNot checkable as stated
Chollet: GPT-4 lacks fluid intelligence, but OpenAI's o3 model has it
“GPT-IV does not have fluid intelligence, for instance, but O-III does.”
Francois CholletApr 3, 2025▶ 5:00Chasing Real AGI: Inside ARC Prize 2025 with Chollet & Knoop
PredictionNot checkable as stated
Chollet: Commercial AI models will increasingly adopt test-time search architectures
“Increasingly, you're gonna see commercial models that use test-time search, where instead of just trying to generate one single COT to adapt to the task, they're actually gonna run through this, you know, search.”
Francois CholletApr 3, 2025▶ 9:47Chasing Real AGI: Inside ARC Prize 2025 with Chollet & Knoop
AssertionSupported
Chollet: Latest base LLMs score zero percent on ARC-AGI-2
“Today the latest base alarms, they're doing something like 10% on ARK-I. But on Arc two, they are doing zero percent.”
Francois CholletApr 3, 2025▶ 10:50Chasing Real AGI: Inside ARC Prize 2025 with Chollet & Knoop
Insight
Chollet: Intelligence should be defined as skill acquisition efficiency
“And yeah, so I, to summarize that, you know, I see intelligence as skill acquisition efficiency. So it's not the fact that you can acquire skills, it's how efficiently You can do it. That's a measure of your intelligence.”
Francois CholletApr 3, 2025▶ 16:06Chasing Real AGI: Inside ARC Prize 2025 with Chollet & Knoop
Opinion
Chollet: OpenAI o3 is the most advanced test-time adaptation model
“And OSTRI best I can tell is the most advanced the most successful test and adaptation model out there at this time.”
Francois CholletApr 3, 2025▶ 17:53Chasing Real AGI: Inside ARC Prize 2025 with Chollet & Knoop
Made with StarZero
Turn any episode into a week of clips.
This entire site, over 400 conversations transcribed, diarized, checked and made playable,
runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the
moments worth sharing, cuts them, captions them, and reframes them for every feed.
We use essential cookies to make the site work. With your permission we
also use analytics cookies (Google Analytics and Mixpanel) to understand
usage and improve StarZero. See our Cookie Policy.
