“I suspect we will see loads of problems with open-ended real world tasks.”
Our reading, the sentence that was checked:
Marcus suspects that OpenAI's GPT-6 Astra will show loads of problems with open-ended real-world tasks, despite its success on ARC-AGI.
Assessment: Can’t be checked No deadline stated on 2026-10-29 Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Hot take on GPT-6 Astra, paragraph after 'What we don’t know is how robust that capability is.'.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment gm-astra-open-ended-task-problems-a2
The wording above is the version this site observed on 2026-10-28. The source may have been edited after 2026-09-03. This page does not claim the wording was captured then.
What the claim commits to
- Kind
- Forecast
- Deadline, as the speaker wrote it
- None stated. This site does not add one.
- Deadline state when assessed
- No deadline stated
- Deadline state on 2026-10-29
- No deadline stated (the release’s reference date)
From the speaker
- I suspect we will see loads of problems with open-ended real world tasks
- Success on ARC-AGI is great and impressive, but not ... proof of AGI
- the post's footnote: 'This hot take is VERY tentative, pending more information about how the systems works'
Our interpretation
- 'I suspect' names a possibility, not a definite expectation, and the footnote calls the whole take very tentative. The policy records such a statement but does not score it.
Counts as supported if: Not scored. The statement is a suspicion with no deadline.
Counts as contradicted if: Not scored. The statement is a suspicion with no deadline.
Retrospective: these criteria were written after the outcome was public.
Current assessment
Did the forecast come true?
Outcome: Can’t be checked
The statement is a recommendation, a value judgment, or too open to test. It is recorded, not scored.
- Evidence as of
- Deadline state when assessed
- No deadline stated
- Assessment recorded
- Policy version
- 2026-10-28.5 (the current policy is 2026-10-28.7; this assessment has not been rechecked under it)
Rationale
On September 3, 2026, writing about OpenAI's GPT-6 Astra, Marcus said its success on ARC-AGI is not proof of AGI and that he suspects we will see loads of problems with open-ended real-world tasks. He called the whole take very tentative. A suspicion with no deadline is recorded and not scored.
Limitations
- This record does not show how Astra has performed on open-ended real-world tasks.
Evidence (0 items)
No evidence item settled this claim by the cutoff.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Hot take on GPT-6 Astra
I suspect we will see loads of problems with open-ended real world tasks.
- Published
- 2026-09-03
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment gm-astra-open-ended-task-problems-a2: Current. Outcome: Can’t be checked. Evidence as of 2026-10-28. Public date not recorded.
Recorded events
Site correctionBy this site
A new assessment with the same outcome replaced the previous one.
Assessment publishedBy this site
First assessment published after both reviews and the final-text check passed.
About assessment gm-astra-open-ended-task-problems-a1, which was not published.