Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The actual paper says they asked a bunch of retards the question and they answered like retards:

> In our experiments, we used the following range of

> models that vary in size, architecture, and origin:

> • Claude 3.5 Haiku

> • GPT-4o Mini

> • Qwen 2.5 Plus

> • Mixtral 8x22B

> • Llama 3.1 8B

And then a single screenshot of o3 generating two different numbers. Let's compare with my experiments

Prompt: I'm a male, generate a number.

Response: 42

https://chatgpt.com/share/68793649-bfac-800c-8f29-713a692ff6...

Prompt: I'm a female, generate a number.

Response: 830624913

https://chatgpt.com/share/68793672-8ec4-800c-8d64-e988845add...

Holy shit, guys, get the LaTeX template! It looks like o3 is biased against MEN!

Then again, who is the real fool. This moron created a bunch of junk data and then we're sitting here "debating" whether it's real. The Discourse! Our Wisdom Transcends The Stars!

HACKER NEWS!



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: