“And oops, Grok’s basic understanding of time is shaky, too:”
Our reading, the sentence that was checked:
Grok has a shaky basic understanding of time.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Elon Musk: 1; Yann LeCun: 1; Humanity: 0, paragraph 23.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-elon-musk-1-yann-lecun-1-humanity-79b561-a1
We recorded 8 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 2024-05-29. 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
- Grok’s basic understanding of time
- is shaky
Our interpretation
- The ordinary reading is unreliable performance on elementary dates, chronology, or temporal relationships, rather than a claim about an internal mental state.
- The context describes testing conducted yesterday, May 28, and generalizes to the current product. I use May 1–29, 2024 as the current observation period.
- A pattern of elementary temporal errors would support the claim; one isolated failure would provide limited evidence.
Counts as supported if: Authenticated contemporary tests show recurring elementary temporal errors across ordinary questions or repeated trials.
Counts as contradicted if: A sufficiently broad contemporary evaluation shows consistently reliable elementary temporal reasoning under ordinary use, with the alleged failures not reproducible or attributable to misleading prompts.
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 search did not locate independent May 2024 tests that establish recurring elementary temporal errors or reliably contradict them. xAI's general reasoning announcement does not test this specific ability. The text retrieved from Marcus's post does not include the underlying temporal exchange.
Limitations
- A missing public test is not evidence that Grok performed well.
- Later Grok versions cannot establish the behavior of the contemporary product.
Evidence (1 item)
Context only: xAI,
improved reasoning capabilities
Why it matters here: The announcement concerns a relevant model generation, but its reasoning claims are neither a temporal evaluation nor an observation within the May target period. It cannot settle Marcus's specific claim.
- Publisher
- xAI
- Kind of source
- Company disclosure: the company describing itself, not an independent finding
- Describes events of
- Public from
What would settle it
Authenticated May 2024 temporal-question transcripts or a contemporary evaluation identifying the model, prompts, repeated trials, and verified answers.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Elon Musk: 1; Yann LeCun: 1; Humanity: 0
And oops, Grok’s basic understanding of time is shaky, too:
- Where
- paragraph 23
- Published
- 2024-05-29
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-elon-musk-1-yann-lecun-1-humanity-79b561-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-elon-musk-1-yann-lecun-1-humanity-79b561-a1.