Pundit ClaimsAI claims by Gary Marcus and Ed Zitron, with the evidence

“That gross violation of spatiotemporal continuity/failure of object permanence is not a one-off, either; it’s something general.”

Sora still appears to have trouble with physics, paragraph 6. The full statement is at the source.

Our reading, the sentence that was checked:

Sora's failures of object permanence and spatiotemporal continuity are general rather than isolated.

Assessment: Supported Evidence as of

Where and when Gary Marcus wrote it

Marcus on AI, Sora still appears to have trouble with physics, paragraph 6.

Said
Source observed
live page, full text, public
Evidence as of
the cutoff for this assessment
Assessment recorded
assessment marcus-sora-still-appears-to-have-trouble-e0f584-a1

We recorded 4 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 2024-12-10. 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

  • gross violation of spatiotemporal continuity/failure of object permanence
  • not a one-off
  • something general
  • wolf-pups, which wink in an and out of existence

Our interpretation

  • The observation is part of the quoted February discussion, so its target is the February 2024 launch model and demonstrations.
  • The plain reading of general, following not a one-off, is a recurring failure mode rather than a defect present in every video or a majority of generations.
  • A contemporaneous developer statement identifying spontaneous appearance as a recurring model weakness can support recurrence without supplying a population-wide failure rate.

Counts as supported if: The launch record documents repeated continuity failures across scenes or identifies them explicitly as a recurring model failure mode.

Counts as contradicted if: A sufficiently comprehensive examination establishes that the alleged continuity failure was isolated, while the other purported examples preserve object existence and identity.

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 launch documentation identifies spontaneous appearances as a model weakness, especially in crowded scenes. That supports the ordinary reading of not a one-off: a recurring failure mode. It does not establish that most videos fail. Independent evidence of successful consistency in selected clips limits a stronger reading, so the interpretation is explicitly flagged.

Limitations

  • Support rests on contemporaneous developer documentation rather than a representative independent audit.
  • General is interpreted as recurring, not universal or predominant.
  • The geometric-consistency study measures a related but different capability.

Evidence (2 items)

  • Supports the claim: OpenAI,

    Animals or people can spontaneously appear, especially in scenes containing many entities.

    Why it matters here: The developer identifies spontaneous appearance as a model weakness associated particularly with crowded scenes. This supports recurrence as a failure mode, without quantifying its prevalence.

    Publisher
    OpenAI
    Kind of source
    Company disclosure: the company describing itself, not an independent finding
    Describes events of
    Public from
  • Context only: Xuanyi Li and colleagues / arXiv,

    This demonstrates the stability and consistency of Sora in preserving physical, imaging, and geometric features over long periods.

    Why it matters here: Selected launch clips retained measurable geometric features over time. This limits a universal reading of Marcus's claim, although feature consistency does not directly test every occluded object's continued existence.

    Publisher
    Xuanyi Li and colleagues / arXiv
    Kind of source
    Preprint, not peer reviewed
    Describes events of
    Public from

Where it was said (1)

Said once in the sources this register covers.

  • : Marcus on AI, Sora still appears to have trouble with physics

    That gross violation of spatiotemporal continuity/failure of object permanence is not a one-off, either; it’s something general.

    Published
    2024-12-10
    Source observed
    , live page
    Access
    full text, public

History

Assessment versions

Recorded events

  1. Assessment publishedBy this site

    First assessment published after both reviews and the final-text check passed.

    About assessment marcus-sora-still-appears-to-have-trouble-e0f584-a1.