“As I told NYT columnist Farhad Manjoo, ChatGPT, like earlier, related systems is “still not reliable, still doesn’t understand the physical world, still doesn’t understand the psychological world and still hallucinates.””
Our reading, the sentence that was checked:
ChatGPT is not reliable, does not understand the physical or psychological world, and hallucinates.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, What to Expect When You’re Expecting … GPT-4, paragraph 3.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-what-to-expect-when-youre-expecting-40b365-a1
We recorded 27 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 2022-12-25. 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
- ChatGPT
- still not reliable
- still doesn’t understand the physical world
- still doesn’t understand the psychological world
- still hallucinates
Our interpretation
- This is a compound claim; evidence of hallucination alone cannot establish all its components.
- The practical reading of understanding is dependable reasoning about physical situations and people's beliefs, intentions, or behavior, rather than consciousness.
- The target period is the initial public release through the post date, reflecting the contemporary system discussed in the post.
Counts as supported if: Contemporary evidence establishes factual unreliability and fabrication, together with substantial failures of practical physical and psychological reasoning.
Counts as contradicted if: Contemporary evaluations establish dependable factual accuracy and robust physical and psychological reasoning. Strong contrary evidence on individual components would warrant a component-specific assessment.
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 launch disclosure supports the unreliability and hallucination components. The stronger claims about physical and psychological understanding remain unsettled by the records verified here. Inconsistent moral advice is not a test of psychological understanding. Partial support without decisive contrary evidence is insufficient for either supported or mixed on the full claim.
Limitations
- The result depends on treating understanding as practical reasoning competence.
- Later models and tests cannot automatically establish the capabilities of December 2022 ChatGPT.
Evidence (2 items)
Supports the claim: OpenAI,
incorrect or nonsensical
Why it matters here: OpenAI acknowledges the factual unreliability and hallucination components. This disclosure does not establish lack of physical or psychological understanding.
- Publisher
- OpenAI
- Kind of source
- Company disclosure: the company describing itself, not an independent finding
- Describes events of
- Public from
Context only: Scientific Reports,
not consistent.
Why it matters here: The study documents inconsistent moral recommendations. It does not test whether ChatGPT can track beliefs or intentions, and therefore cannot settle the psychological-understanding component.
- Publisher
- Scientific Reports
- Kind of source
- Peer-reviewed paper
- Describes events of
- Public from
What would settle it
Dated, independently assessed tests of the original ChatGPT covering physical situations and people's beliefs or intentions, with successes and failures reported under explicit competence criteria.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, What to Expect When You’re Expecting … GPT-4
As I told NYT columnist Farhad Manjoo, ChatGPT, like earlier, related systems is “still not reliable, still doesn’t understand the physical world, still doesn’t understand the psychological world and still hallucinates.”
- Where
- paragraph 3
- Published
- 2022-12-25
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-what-to-expect-when-youre-expecting-40b365-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-what-to-expect-when-youre-expecting-40b365-a1.