“Notwithstanding the rumors about Google Imagen, nobody has yet publicly demonstrated a machine that can relate the meanings of sentences to their parts the way a five-year-old child can.”
Our reading, the sentence that was checked:
No one, Imagen included, has publicly shown a machine that relates sentence meanings to their parts as well as a five-year-old.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Did GoogleAI Just Snooker One of Silicon Valley’s Sharpest Minds?, paragraph 32.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-did-googleai-just-snooker-one-of-648cfa-a1
We recorded 12 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 2022-09-14. 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
- nobody has yet publicly demonstrated
- relate the meanings of sentences to their parts
- the way a five-year-old child can
- Notwithstanding the rumors about Google Imagen
Our interpretation
- The claim concerns demonstrations publicly available through September 14, 2022.
- The ordinary reading is robust sentence-composition ability comparable to a typical five-year-old, without requiring the same internal mechanism.
- An adult or unspecified human benchmark is relevant background but cannot silently replace the stated child comparison.
- A selected successful example is insufficient to demonstrate the general ability described.
Counts as supported if: A defensible survey of public systems and age-appropriate evaluations establishes that none demonstrated comparable sentence-composition ability by the post date.
Counts as contradicted if: A publicly documented system available by the post date demonstrates comparable performance to five-year-olds across controlled, varied sentence-composition tasks.
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
Winoground supports concern about compositional limitations, but its crowdworker baseline does not establish a five-year-old standard. The search found no qualifying contemporary demonstration of child-level parity. That search result alone is insufficient to establish the universal negative.
Limitations
- The named age threshold is not measured by the cited benchmark.
- Restricted task success would not necessarily establish the breadth of ability described.
Evidence (1 item)
Context only: arXiv; Tristan Thrush and colleagues,
a human baseline using crowdworkers
Why it matters here: Winoground documents a substantial gap between tested models and its human baseline. That baseline uses crowdworkers and supplies no five-year-old comparison, so it does not directly resolve Marcus's stated threshold.
- Publisher
- arXiv; Tristan Thrush and colleagues
- Kind of source
- Preprint, not peer reviewed
- Describes events of
- Public from
What would settle it
A public demonstration available by September 14, 2022 with an appropriate child comparison, or a well-supported contemporary survey establishing the absence of such demonstrated capability.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Did GoogleAI Just Snooker One of Silicon Valley’s Sharpest Minds?
Notwithstanding the rumors about Google Imagen, nobody has yet publicly demonstrated a machine that can relate the meanings of sentences to their parts the way a five-year-old child can.
- Where
- paragraph 32
- Published
- 2022-09-14
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-did-googleai-just-snooker-one-of-648cfa-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-did-googleai-just-snooker-one-of-648cfa-a1.