“The first author’s nine-year-old can do five digit multiplication better than an LLM.”
Our reading, the sentence that was checked:
The first author's own nine-year-old child can do five-digit multiplication better than an LLM.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Reports of the birth of AGI are greatly exaggerated, paragraph 16.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-reports-of-the-birth-of-agi-are-greatly-02608f-a1
We recorded 11 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 2023-10-18. 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
- the first author's nine-year-old (scope, stated by the speaker)
From the speaker
- The first author’s nine-year-old
- five digit multiplication
- better than an LLM
Our interpretation
- This is a comparison involving the author's particular child, not an average nine-year-old.
- Five-digit multiplication ordinarily means multiplying two five-digit integers.
- Better is read primarily as a higher proportion of correct answers on comparable problems, with time and permitted aids disclosed.
- The claim concerns the child's ability at the post date. It is not a conditional forecast.
- An LLM is unspecified; a valid comparison must identify the contemporary model and its configuration.
Counts as supported if: A documented comparison shows the named child answering comparable five-digit multiplication problems more accurately than an identified contemporary LLM under disclosed conditions.
Counts as contradicted if: A documented comparison under the claimed conditions shows the identified LLM matching or exceeding the child's accuracy.
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
Contemporary research documents arithmetic weaknesses, but the claim compares an LLM with a particular child. The searches did not locate independently inspectable results for that child or a matched comparison. General model failures cannot fill that gap, and the absence of a public test does not show the claim was false.
Limitations
- A private comparison may have occurred.
- Unspecified model and testing conditions prevent reconstruction of the asserted comparison.
Evidence (1 item)
Context only: arXiv; Dziri and colleagues,
Yet, these models simultaneously show failures on surprisingly trivial problems.
Why it matters here: The paper investigates multi-digit multiplication among several reasoning tasks. Such model-side evidence cannot establish a comparison with an untested individual child.
- Where
- Abstract
- Publisher
- arXiv; Dziri and colleagues
- Kind of source
- Preprint, not peer reviewed
- Describes events of
- Public from
What would settle it
Dated, inspectable records of the child's and the identified contemporary model's answers to comparable five-digit multiplication problems, with scoring and permitted aids disclosed.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Reports of the birth of AGI are greatly exaggerated
The first author’s nine-year-old can do five digit multiplication better than an LLM.
- Where
- paragraph 16
- Published
- 2023-10-18
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-reports-of-the-birth-of-agi-are-greatly-02608f-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-reports-of-the-birth-of-agi-are-greatly-02608f-a1.