“failed, multiple times, to include a full list of all US states”
Our reading, the sentence that was checked:
In Marcus's test, the free version of ChatGPT failed several times to produce a complete list of all 50 US states.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, ChatGPT in Shambles, paragraph 30.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-chatgpt-in-shambles-0811ec-a2
We recorded 6 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 2025-02-04. 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
- in a 10-minute test session (qualifier, stated by the speaker)
From the speaker
- ChatGPT
- failed, multiple times
- to include a full list of all US states
- over the course of 10 minutes
- latest (unpaid) version of ChatGPT
Our interpretation
- Read as: in Marcus's session on or about 2025-02-04, at least two ChatGPT answers that were meant to list every US state left out one or more states.
- The primary record is the shared conversation Marcus linked.
Counts as supported if: The transcript, or an independent check of it, shows two or more state tables that each left out at least one of the 50 states.
Counts as contradicted if: The transcript shows that at most one table left out states.
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 about one session with the free version of ChatGPT on or about 4 February 2025. Marcus describes the session as lasting 10 minutes. Under the contract, the claim is supported only if the shared transcript, or an independent check of it, shows two or more state tables that each left out at least one state. The evidence includes neither the transcript nor such a check. A post by Benjamin Todd, available on 9 February 2025, says "GPT-4o misses out a bunch of states" (e1). It does not say how many of Marcus's tables left out states. It also does not say whether Todd looked at Marcus's transcript. A reader comment dated 5 February 2025 says the reader's own GPT-4o run left out states (e2). That was a different session, so it does not show what happened in Marcus's session. The evidence neither confirms nor rules out two or more incomplete tables.
Limitations
- The shared transcript linked in Marcus's post was not found, so none of his tables could be checked against the list of 50 states.
- e1 does not show whether its author checked Marcus's transcript, or how many of Marcus's tables left out states.
- e2 describes a different session and cannot show what Marcus's session produced.
Evidence (2 items)
Context only: Benjamin Todd (Substack),
GPT-4o misses out a bunch of states.
Why it matters here: A critic accepts that GPT-4o left out states, but he does not say whether it happened more than once in Marcus's session or whether he looked at the transcript.
- Publisher
- Benjamin Todd (Substack)
- Kind of source
- Secondary summary
- Describes events of
- Public from
Context only: Substack reader comment,
States missing. Lists a state as formerly missing that wasn't.
Why it matters here: A separate GPT-4o run that showed the same kind of failure. It is not evidence about Marcus's own session.
- Publisher
- Substack reader comment
- Kind of source
- Secondary summary
- Describes events of
- Public from
What would settle it
The chatgpt.com conversation shared in Marcus's post, or an independent check of it, with each state table compared against the list of 50 US states.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, ChatGPT in Shambles
failed, multiple times, to include a full list of all US states
- Where
- paragraph 30
- Published
- 2025-02-04
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-chatgpt-in-shambles-0811ec-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.