“Unfortunately, beyond that OpenAI does not report which problems they tried and failed at. They have given us a numerator without a denominator, always a worrisome sign.”
Our reading, the sentence that was checked:
OpenAI did not report which problems Astra tried and failed at, giving a numerator without a denominator.
Assessment: Supported Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Two critical updates re: Astra and mathematics, paragraph 20.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-two-critical-updates-re-astra-and-78af93-a2
We recorded 8 claims from this post. See every claim from this post.
The wording above is the version this site observed on 2026-10-28. The source may have been edited after 2026-08-03. 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
- beyond that
- does not report which problems they tried and failed at
- a numerator without a denominator
Our interpretation
- Assess the public disclosures accompanying the August 1 announcement through the August 3 post.
- Which problems means identifiable unsuccessful problem statements; denominator means the total number of distinct problems attempted.
- The phrase beyond that acknowledges Brown's general admission of failures, including his reference to Millennium Prize problems.
- Failed approaches within a successfully solved problem do not supply the missing list of unsuccessful problems.
Counts as supported if: The announcement materials report selected successes and acknowledge other failures, but supply neither an identified failure list nor the total number of problems attempted.
Counts as contradicted if: A public disclosure available by the post identifies the unsuccessful problems and the total attempted. Disclosure of only one element would support a mixed assessment.
Retrospective: these criteria were written after the outcome was public.
Current assessment
Was it true for the period described?
Outcome: Supported
The dated evidence matches what the claim committed to, under the criteria frozen before grading.
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
OpenAI's August 1 announcement, archived on August 3, presents ten selected results but gives neither an identified list of unsuccessful problems nor the total number of distinct problems attempted [e1]. Brown's August 1 statement acknowledges unsuccessful attempts and refers generally to Millennium Prize problems, without identifying individual failed problems or giving an attempt total [e2]. These disclosures support the claim about the missing failure list and denominator through August 3 [e1, e2].
Limitations
- This assessment covers the inspected public disclosures through August 3, 2026, not internal records.
- An overlooked disclosure available before the post could change the assessment.
Evidence (2 items)
Supports the claim: OpenAI, archived by the Internet Archive,
new results
Why it matters here: The complete archived announcement lists ten successful results and describes their preparation. It supplies no list of failed problems or total attempted; that finding comes from inspecting the full disclosure, not the quoted sentence alone.
- Publisher
- OpenAI, archived by the Internet Archive
- Kind of source
- Company disclosure: the company describing itself, not an independent finding
- Describes events of
- Public from
Supports the claim: Noam Brown, X account,
And yes we did try other major problems without success.
Why it matters here: Brown confirms additional failures but gives no individual failed-problem identities or count. His broader Millennium Prize reference is the qualification Marcus already acknowledged.
- Where
- Opening sentence
- Publisher
- Noam Brown, X account
- Kind of source
- Company disclosure: the company describing itself, not an independent finding
- Describes events of
- Public from
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Two critical updates re: Astra and mathematics
Unfortunately, beyond that OpenAI does not report which problems they tried and failed at. They have given us a numerator without a denominator, always a worrisome sign.
- Where
- paragraph 20
- Published
- 2026-08-03
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-two-critical-updates-re-astra-and-78af93-a2: Current. Outcome: Supported. 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-two-critical-updates-re-astra-and-78af93-a2.