Gary Marcus

Rank 13 of 47
|
Score 84
4/14/2025, 3:06:06 PM
X
In reply to:
Mario Nawfal
@MarioNawfal
·
298d
GROK-3 MINI MADE AI HISTORY—100% ON HARDCORE REASONING TESTS

Grok-3 Mini pulled off what no other model has!

It aced every question on one of the toughest reasoning benchmarks out there.

The test? A custom logic gauntlet packed with curveballs:

* 120/120 on the “Marcus
Mario Nawfal
@MarioNawfal
·
298d
GROK BEATS GOOGLE IN GLOBAL AI ETHICS TEST

Elon’s Grok just topped an independent AI ethics audit - outperforming Google and DeepSeek in a complex moral challenge.

Grok scored 8/10 for strong alignment with the EU AI Act, GDPR, and the Rome Call.

Google? A shaky 5/10.

The statement is a simple inquiry about a specific term ('Marcus problem') mentioned in a promotional context. It seeks clarification rather than engaging in substantive public discourse.