Get the latest tech news

A test for AGI is closer to being solved — but it may be flawed


A test for AGI, ARC-AGI, is closer to being solved — but the test may be flawed, its creators, including notable AI figure Francois Chollet, admit.

“If you need to be trained on many examples of a pattern, even if it’s implicit, in order to learn a reusable representation for it, you’re memorizing,” Chollet argued in another post. To incentivize research beyond LLMs, in June, Chollet and Zapier co-founder Mike Knoop launched a $1 million competition to build open source AI capable of beating ARC-AGI. “We will continue to direct the efforts of the research community towards what we see as the most important unsolved problems in AI, and accelerate the timeline to AGI,” Chollet wrote in an X post.

Get the Android app

Or read this on TechCrunch

Read more on:

Photo of test

test

Photo of agi

agi

Related news:

News photo

Microsoft’s AI boss and Sam Altman disagree on what it takes to get to AGI

News photo

OpenAI seeks to unlock investment by ditching 'AGI' clause with Microsoft

News photo

OpenAI considers ditching provision that would prevent AGI from being used for commercial gain