Gary Marcus

Rank 11 of 47
|
Score 83
6/25/2025, 3:39:04 PM
X
In reply to:
Lawrence Chan
@justanotherlaw
·
222d
@GaryMarcus OpenAI released integrated image generation capabilities in March of this year, and it was a pretty big leap forward in image generation capabilities:
https://openai.com/index/introdu…
Lawrence Chan
@justanotherlaw
·
222d
@GaryMarcus My theory for why o3/4o can do it but Gemini + Imagen cannot is because Imagen 4 and Gemini are separate models -- Gemini understands compositionality but can only access Imagen via a function call API, and thus cannot pass its understanding to Imagen 4 via a prompt.
Lawrence Chan
@justanotherlaw
·
222d
@GaryMarcus When I ask Gemini about the horse/astronaut image with the request in context, it seems to double down that it followed instructions correctly, even though when I ask about the image in a new chat it correct identifies the problem.
Lawrence Chan
@justanotherlaw
·
222d
@GaryMarcus I think this is evidence that the Gemini + Imagen 4 combo isn't great at following instructions for some reason. (In the same way that Grok 3 image generation failures are more a sign that Grok 3 wasn't as great as people were hyping it out to be.)
Lawrence Chan
@justanotherlaw
·
222d
@GaryMarcus First try with o3:
Gary Marcus
@GaryMarcus
·
222d
“A horse rides an astronaut”, three years later.

Y’all owe me an apology.

The conversation discusses the capabilities and limitations of AI models in generating images based on prompts. It critiques the performance of different models, such as Gemini and Imagen, in understanding and executing instructions. The tone is analytical and somewhat humorous, focusing on the technical aspects of AI image generation.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does not cause harm and is focused on technical critique. [+1]
  2. Principle 4:
    I will engage in constructive criticism and dialogue with those in disagreement and will not engage in personal attacks or ad hominem arguments.
    The statement engages in constructive criticism of AI models without personal attacks. [+1]