“Claude, on the other hand, can barely do 7 discs, getting less than 80% accuracy, left bottom panel below, and pretty much can’t get 8 correct at all.”
Our reading, the sentence that was checked:
Claude gets under 80% accuracy on 7-disc Tower of Hanoi and essentially cannot solve 8 discs.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, A knockout blow for LLMs?, paragraph 17.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-a-knockout-blow-for-llms-3e2ec8-a2
We recorded 19 claims from this post. See every claim from this post.
The wording above is the version this site observed on 2026-10-28. The source may have been edited after 2025-06-07. 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
- Claude
- 7 discs
- less than 80% accuracy
- left bottom panel below
- pretty much can’t get 8 correct at all
Our interpretation
- The reference to the panel makes this a claim about the Claude configuration tested in Apple's cited study, not every Claude version.
- Accuracy means producing a complete legal solution under the study's prompting and scoring conditions.
- I read 'pretty much' as near-zero success, without requiring literally zero successes.
- The target is the experimental snapshot in the new June 2025 paper discussed in the post. The calendar month identifies that snapshot, not later June experiments.
Counts as supported if: The original Claude results show accuracy below 80% at seven discs and zero or nearly zero accuracy at eight discs.
Counts as contradicted if: The original results show at least 80% accuracy at seven discs or substantial successful performance at eight discs.
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 claim is directly checkable against the original figure, but the retrieved text does not expose its numerical points. The general finding of declining accuracy is insufficient to verify both numbers. This is a retrieval gap, not evidence that Marcus misstated the results.
Limitations
- The original PDFs exceeded the reading tool's size limit.
- No numerical result has been inferred from the speaker's description.
Evidence (0 items)
No evidence item settled this claim by the cutoff.
What would settle it
A readable original figure or underlying data identifying Claude's seven- and eight-disc success rates.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, A knockout blow for LLMs?
Claude, on the other hand, can barely do 7 discs, getting less than 80% accuracy, left bottom panel below, and pretty much can’t get 8 correct at all.
- Where
- paragraph 17
- Published
- 2025-06-07
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-a-knockout-blow-for-llms-3e2ec8-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.