AI Models Can’t Even Count Rocks?! Shocking o3 vs. Gemini 2.5 Pro Showdown—Brought to life by Avonetics.com episode artwork

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.

Episode metadata supplied by the publisher feed · Published Apr 17, 2025

Embed this episode

NOW PLAYING

AI Models Can’t Even Count Rocks?! Shocking o3 vs. Gemini 2.5 Pro Showdown—Brought to life by Avonetics.com

0:00 10:25

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Beaker Banter?

This episode is 10 minutes long.

When was this Beaker Banter episode published?

This episode was published on April 17, 2025.

Can I download this Beaker Banter episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!