EPISODE · Apr 17, 2025 · 10 MIN
AI Models Can’t Even Count Rocks?! Shocking o3 vs. Gemini 2.5 Pro Showdown—Brought to life by Avonetics.com
from Beaker Banter · host Beaker Banter
When OpenAI’s o3 model spent ages failing to count rocks in an image, Avonetics users erupted with disbelief. How did Gemini 2.5 Pro and 4o stack up? Theories exploded: Are these AIs secretly Googling answers or just hilariously bad at basic math? This wild thread exposes the jaw-dropping limits of cutting-edge AI, proving even “smart” models trip over pebbles. Spoiler: The results will make you question everything. For advertising opportunities, visit Avonetics.com.
What this episode covers
When OpenAI’s o3 model spent ages failing to count rocks in an image, Avonetics users erupted with disbelief. How did Gemini 2.5 Pro and 4o stack up? Theories exploded: Are these AIs secretly Googling answers or just hilariously bad at basic math? This wild thread exposes the jaw-dropping limits of cutting-edge AI, proving even “smart” models trip over pebbles. Spoiler: The results will make you question everything. For advertising opportunities, visit Avonetics.com.
NOW PLAYING
AI Models Can’t Even Count Rocks?! Shocking o3 vs. Gemini 2.5 Pro Showdown—Brought to life by Avonetics.com
No transcript for this episode yet
Similar Episodes
Jun 21, 2026 ·31m
Jun 21, 2026 ·65m
Jun 20, 2026 ·45m