Gary Marcus

Rank 13 of 47
|
Score 84
6/25/2025, 9:42:46 PM
X
In reply to:
Lawrence Chan
@justanotherlaw
·
224d
@GaryMarcus Yeah, I guess my last tweet (which talked about how o3 failed a previous benchmark of yours involving circling “r”s) didn’t send. I’m not saying o3 image gen is perfect — far from it. I’m just saying that the horse — astronaut thing isn’t a problem for it.
Gary Marcus
@GaryMarcus
·
224d
@justanotherlaw
Lawrence Chan
@justanotherlaw
·
224d
@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
·
224d
@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
·
224d
@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
·
224d
@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.)

The statement is part of a technical discussion about AI image generation models and their capabilities. It reflects a user's experience with a specific model and highlights challenges faced when deviating from well-known examples. The tone is analytical and focused on understanding model performance.

  1. Principle 1:
    I will strive to do no harm with my words and actions.
    The statement does no harm and is focused on technical analysis. [+1]
  2. Principle 3:
    I will use my words and actions to promote understanding, empathy, and compassion.
    The statement promotes understanding by sharing personal experiences with AI models. [+1]
  3. 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 dialogue by discussing technical challenges without personal attacks. [+1]