←back to thread

Getting 50% (SoTA) on Arc-AGI with GPT-4o

(redwoodresearch.substack.com)
394 points tomduncalf | 4 comments | 17 Jun 24 21:51 UTC | HN request time: 0s | source
Show context
bashfulpup ◴[17 Jun 24 22:59 UTC] No.40712167[source]▶
I looked at the website and have no idea how Arc is supposed to be AGI.

Can someone explain?

replies(2): >>40712815 #>>40712975 #
TheDudeMan ◴[18 Jun 24 00:30 UTC] No.40712815[source]▶
It is necessary but not sufficient.

If you can't do ARC, you aren't general enough. But even if you can do ARC, you still might not be general enough.

replies(1): >>40712927 #
Workaccount2 ◴[18 Jun 24 00:48 UTC] No.40712927[source]▶
It's also possible that you are an AGI and simply cannot pass ARC.
replies(1): >>40713114 #
TheDudeMan ◴[18 Jun 24 01:18 UTC] No.40713114{3}[source]▶
How so? If there is a task that humans can do but the AI cannot, I would not call it AGI. But that's just my definition.
replies(1): >>40713172 #
1. awwaiid ◴[18 Jun 24 01:29 UTC] No.40713172{4}[source]▶
Yeah but if my brother can't pass it, that doesn't mean he is NOT human.
replies(3): >>40713646 #>>40713654 #>>40714594 #
2. Jensson ◴[18 Jun 24 02:57 UTC] No.40713646[source]▶
Could he pass it if he was educated to do the task from birth? Human level intelligence includes being able to be educated, the ML models we have done so far can't be educated so have to match the level of educated humans to compare.

General intelligence as we know it requires ability to receive education.

3. infgeoax ◴[18 Jun 24 02:58 UTC] No.40713654[source]▶
Isn't chatGPT already proven to be smarter than many of us in many ways?
4. TheDudeMan ◴[18 Jun 24 06:20 UTC] No.40714594[source]▶
I said AGI. I did not say human.