“ChatGPT simply cannot reason well enough to to do this; as I have documented in previous essays, it has demonstrably misunderstood physics, biology, psychology, medicine, and so forth.”
Our reading, the sentence that was checked:
ChatGPT cannot reason well enough to make a substantive scientific contribution and has misunderstood physics, biology, psychology, and medicine.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Scientists, please don’t let your chatbots grow up to be co-authors, paragraph 17.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-scientists-please-dont-let-your-chatbots-1e17cf-a2
We recorded 11 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 2023-01-14. 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
- cannot reason well enough
- making a substantive scientific contribution
- demonstrably misunderstood physics, biology, psychology, medicine
- current understanding
Our interpretation
- Assess the early ChatGPT during the six-week period discussed in the post, through January 14, 2023.
- A substantive contribution means meaningful intellectual work on a scientific question, including collaboration with human researchers.
- The claim combines a broad inability assertion with examples of disciplinary misunderstanding. These components require separate evidence.
- Incorrect scientific explanations demonstrate errors; they do not by themselves establish inability to contribute to research.
- Authorship policies and requirements for accountability do not measure reasoning ability.
Counts as supported if: Contemporary evaluations establish the asserted scientific reasoning limitation and documented misunderstandings in the named disciplines. Evidence must connect the reasoning limitation to inability to make a substantive contribution.
Counts as contradicted if: A verified contemporary research contribution demonstrates sufficient reasoning for substantive scientific work. Correct answers to some examination questions alone do not establish such a contribution.
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
A January 1, 2023 parasitology test documented incorrect explanations, supporting the biological and medical error component [e1]. It did not test whether ChatGPT could make a substantive scientific contribution [e1]. A finance study reported favorable ratings for generated research proposals, but its accessible revised version does not establish a verified contribution dated to November 30, 2022–January 14, 2023 [e2]. These studies establish neither the broader inability claim nor a decisive contemporary counterexample [e1, e2].
Limitations
- The evidence does not independently establish misunderstandings in physics and psychology [e1, e2].
- The parasitology results cannot be generalized directly to other subjects and do not measure research capability [e1].
- The finance study leaves the relevant output dates and validation of a substantive contribution unresolved [e2].
Evidence (2 items)
Supports the claim: Journal of Educational Evaluation for Health Professions,
contained incorrect information.
Why it matters here: The December 15 version produced incorrect parasitology explanations, supporting the biological and medical error component. The study also found correct answers and acceptable explanations, and did not test ability to make a research contribution.
- Publisher
- Journal of Educational Evaluation for Health Professions
- Kind of source
- Peer-reviewed paper
- Describes events of
- Public from
Context only: Finance Research Letters; copy hosted by Abu Dhabi University,
‘succeed’.
Why it matters here: Favorable reviewer assessments of generated research proposals weigh against a blanket inability claim. The accessible revised study neither dates each interaction precisely nor establishes a completed scientific contribution.
- Publisher
- Finance Research Letters; copy hosted by Abu Dhabi University
- Kind of source
- Peer-reviewed paper
- Describes events of
- Public from
What would settle it
An independently verified substantive scientific contribution using ChatGPT outputs dated November 30, 2022–January 14, 2023 would contradict the inability claim. Support would require contemporary evaluations connecting reasoning limitations to inability to contribute, together with independently checked errors in the named disciplines.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Scientists, please don’t let your chatbots grow up to be co-authors
ChatGPT simply cannot reason well enough to to do this; as I have documented in previous essays, it has demonstrably misunderstood physics, biology, psychology, medicine, and so forth.
- Where
- paragraph 17
- Published
- 2023-01-14
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-scientists-please-dont-let-your-chatbots-1e17cf-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.
About assessment marcus-scientists-please-dont-let-your-chatbots-1e17cf-a2.