This is it! The Super Bowl of LLM image model testing. In this episode, we test three leading closed-source image models with loaded prompts to see how biased they really are.

Which one do you think is the most reliable? Which one has the most extreme bias in its results?

This episode is a must listen.

*******

Links from the episode:

Google's past issues with primates

https://www.forbes.com/sites/mzhang/2015/07/01/google-photos-tags-two-african-americans-as-gorillas-through-facial-recognition-software/