“In such cases, DALL-E Mini typically generates images of bowls of cucumbers, and only cucumbers, leaving out the tomatoes altogether (where a human might reasonably expect there to be at least two, given the plural).”
Our reading, the sentence that was checked:
Given comparative prompts such as 'more cucumbers than tomatoes', DALL-E Mini usually leaves out the tomatoes entirely.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Three ideas from linguistics that everyone in AI should know, paragraph 51.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-three-ideas-from-linguistics-that-b6010a-a2
We recorded 26 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 2022-06-22. 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)
From the speaker
- DALL-E Mini typically generates
- bowls of cucumbers, and only cucumbers
- leaving out the tomatoes altogether
- the bowl has more cucumbers than tomatoes
Our interpretation
- Typically means that more than half of representative outputs omit tomatoes entirely.
- The main test is the quoted more-cucumbers prompt. Related comparative prompts should be reported separately rather than pooled to change its result.
- A tomato outside the bowl is a placement error, not complete omission.
- The surrounding reference to experiments presently being conducted places the observation in June 2022 before publication. June 1 through June 22 is an approximate month-to-date window, not a reported experiment schedule.
Counts as supported if: Representative outputs from the contemporary DALL-E Mini version show complete tomato omission in more than half of trials for the quoted prompt, with comparable results for any broader prompt class asserted.
Counts as contradicted if: Representative outputs show that tomatoes are present in at least half of trials, with enough observations to distinguish that result from sampling uncertainty.
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
The supplied packet contains no independently validated outputs or trial denominator for the quoted prompt, and it does not identify the contemporary checkpoint or sampling settings [marcus-three-ideas-from-linguistics-that-b6010a-p1, stated gaps]. The claimed frequency of complete tomato omission therefore remains unverified.
Limitations
- The evidence establishes neither a majority omission rate nor a rate sufficient to contradict the claim.
- The approximate June 1–22, 2022 target window does not identify the actual trial dates.
- Tomatoes outside the bowl must be scored separately from complete tomato omission.
Evidence (0 items)
No evidence item settled this claim by the cutoff.
What would settle it
Independently validated original trial records, or a representative replication using the identified contemporary checkpoint and sampling settings. Retain all outputs and the denominator, independently score tomato presence, cucumber presence and bowl placement, and determine whether complete tomato omission exceeds half of outputs with adequate sampling certainty. Report related prompts separately.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Three ideas from linguistics that everyone in AI should know
In such cases, DALL-E Mini typically generates images of bowls of cucumbers, and only cucumbers, leaving out the tomatoes altogether (where a human might reasonably expect there to be at least two, given the plural).
- Where
- paragraph 51
- Published
- 2022-06-22
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-three-ideas-from-linguistics-that-b6010a-a2: 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-three-ideas-from-linguistics-that-b6010a-a2.