“Nine more tries, and only one very marginal success (top right corner):”
Our reading, the sentence that was checked:
Stable Diffusion produced only one very marginal success in nine further attempts at a part-function prompt.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Form, function, and the giant gulf between drawing a picture and understanding the world, paragraph 31.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-form-function-and-the-giant-gulf-67939d-a1
We recorded 6 claims from this post. See every claim from this post.
The wording above is the version this site observed on 2026-10-29. The source may have been edited after 2022-09-18. This page does not claim the wording was captured then.
What the claim commits to
- Kind
- Observation
- Deadline, as the speaker wrote it
- None stated. This site does not add one.
- Deadline state when assessed
- No horizon
- Deadline state on 2026-10-29
- No horizon (the release’s reference date)
Conditions
- prompt: sketch a person and make the parts that hold things purple (qualifier, stated by the speaker)
From the speaker
- Nine more tries
- only one very marginal success
- top right corner
- sketch a person and make the parts that hold things purple
Our interpretation
- The claim concerns the specific nine additional outputs displayed with the post, rather than Stable Diffusion's general success rate.
- The ordinary intended target is the person's hands. A marginal success would weakly identify and color those parts while retaining substantial defects.
- The batch is assigned to the September 18 demonstration because the surrounding narrative describes testing that morning. Exact generation timestamps are not given.
- Independent image scoring can test the count; repeating the generation today cannot verify this historical batch.
Counts as supported if: Independent inspection of the identified nine-image batch finds exactly one weak success, in the top-right position, and no other successful output.
Counts as contradicted if: Independent inspection of that same batch finds a different success count, a clearly successful image rather than merely a marginal one, or a different location for the sole qualifying image.
Retrospective: these criteria were written after the outcome was public.
Current assessment
Was it true for the period described?
Outcome: Unresolved
The record was checked, and the evidence available by the cutoff does not settle it.
Scored on a plain reading. The speaker named no measure for this claim, so it was judged on the reading an informed reader would take, stated below under our interpretation. Both reviews had to find that reading fair.
- Evidence as of
- Deadline state when assessed
- No horizon
- Assessment recorded
- Policy version
- 2026-10-28.7
Rationale
This is a claim about nine particular outputs. The retrieved sources repeat Marcus's count but do not independently verify it, and their plain text does not expose the images for scoring. General evidence of Stable Diffusion's limitations cannot establish that exactly one of these nine was a marginal success.
Limitations
- Success grading includes a subjective boundary.
- Fresh generations would test the model, not the reported historical count.
Evidence (0 items)
No evidence item settled this claim by the cutoff.
What would settle it
The original nine-image batch with confirmed layout and an independent assessment of each image under a stated rubric for purple hands and marginal success.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Form, function, and the giant gulf between drawing a picture and understanding the world
Nine more tries, and only one very marginal success (top right corner):
- Where
- paragraph 31
- Published
- 2022-09-18
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-form-function-and-the-giant-gulf-67939d-a1: Current. Outcome: Unresolved. Evidence as of 2026-10-28. Public date not recorded.
Recorded events
Assessment publishedBy this site
First assessment published after both reviews and the final-text check passed.
About assessment marcus-form-function-and-the-giant-gulf-67939d-a1.