Sebastian Moore

[Sebastian Moore @SebastianMek8]

@Alokkumarzz Send

[Sebastian Moore @SebastianMek8]

@bnafOg @elonmusk I understand your feedback, thank you. Did you see all of the 3 responses I sent?

[Sebastian Moore @SebastianMek8]

@bnafOg @elonmusk At what point does it stop being “just a benchmark result” and start later suggesting something more architectural?

[Sebastian Moore @SebastianMek8]

@bnafOg @elonmusk How should we interpret a result that is materially above the current reported range, but;
- is fully ARC-evaluated (private/semi-private sets),
- comes from a single model (low millions of parameters),
- and doesn’t rely on task specific scaffolding?

[Sebastian Moore @SebastianMek8]

@cb_doge @bridgebench How does Grok perform on ARC-AGI-3? This is the only legitimate test of REAL reasoning in novel environments. Can you match our score of 15.70%?

[Sebastian Moore @SebastianMek8]

@ceo_spaceX_chat There is no fight more worthy of fighting!

[Sebastian Moore @SebastianMek8]

@ceo_spaceX_chat A. 1m%

[Sebastian Moore @SebastianMek8]

@ceo_spaceX_chat Yes

[Sebastian Moore @SebastianMek8]

@elonmusk Hi Elon, best wishes from Athens, Greece!
You are my first ever post!!
I’m curious if you are familiar with the ARC-AGI-3 test? Have emailed you at [email protected]

[Sebastian Moore @SebastianMek8]

Hi Elon, best wishes from Athens, Greece!
You are my first ever post!!
I’m curious if you are familiar with the ARC-AGI-3 test?