“More evidence against his claims just keeps piling up.”
Our reading, the sentence that was checked:
Evidence against Hinton's claims that GenAI understands and doesn't store things keeps accumulating.
Assessment: Supported Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Further Trouble in Hinton City, paragraph 2.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-further-trouble-in-hinton-city-1fb335-a1
We recorded 4 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 2024-02-08. 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
- More evidence
- keeps piling up
- GenAI systems don’t store things and do understand them
Our interpretation
- The ordinary reading is that additional empirical findings challenge categorical claims about storage and reliable conceptual understanding. It does not require proving that generative AI has no understanding whatsoever.
- The target is the cumulative public research record through publication. No starting date is stated; this is not a claim about experiments conducted only during the preceding two days.
Counts as supported if: Successive public studies document recoverable training content or failures under meaning-preserving changes, adding empirical grounds for questioning the categorical claims.
Counts as contradicted if: The supposed additional findings are absent, materially misrepresented, or invalidated, leaving no documented accumulation of relevant evidence.
Retrospective: these criteria were written after the outcome was public.
Current assessment
Was it true for the period described?
Outcome: Supported
The dated evidence matches what the claim committed to, under the criteria frozen before grading.
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
Successive public studies documented fragile responses to meaning-preserving changes and recoverable training content. That supports the ordinary claim that relevant contrary evidence was accumulating. It does not establish Marcus's stronger suggestion that these results rule out understanding.
Limitations
- The result depends on reading the statement as an evidentiary observation rather than a conclusive theory of understanding.
- Event dates identify when the cited findings entered the public research record.
Evidence (2 items)
Supports the claim: arXiv; Sclar and colleagues,
Sensitivity remains
Why it matters here: The public study documents sensitivity to meaning-preserving formatting changes. This supplies evidence of fragile generalization, although it does not establish an absence of understanding.
- Publisher
- arXiv; Sclar and colleagues
- Kind of source
- Preprint, not peer reviewed
- Describes events of
- Public from
Supports the claim: arXiv; Nasr and colleagues,
practical attacks
Why it matters here: This later public report adds evidence that trained language models retain recoverable training content. Its findings bear directly against a categorical denial of effective storage.
- Publisher
- arXiv; Nasr and colleagues
- Kind of source
- Preprint, not peer reviewed
- Describes events of
- Public from
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Further Trouble in Hinton City
More evidence against his claims just keeps piling up.
- Where
- paragraph 2
- Published
- 2024-02-08
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-further-trouble-in-hinton-city-1fb335-a1: Current. Outcome: Supported. 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-further-trouble-in-hinton-city-1fb335-a1.