“You also wind up with humans with six fingers, humans with three arms, weird walking gaits, ants with four legs, etc because there is no underlying model of the physiological structure of an ant or a human being.”
Our reading:
Sora produces anatomical errors such as six-fingered humans and four-legged ants because it has no underlying model of physiological structure.
Assessment: Unresolved
What happened
Does the evidence support the cause?
Outcome: Unresolved
We checked, and the evidence so far doesn’t settle it.
Judged on a plain reading. They named no measure, so we used the reading a typical informed reader would take. It is spelled out under “How we judged it”.
Evidence up to . Checked .
Why
The proposed cause is not established. Anatomical mistakes would show imperfect outputs, but would not by themselves demonstrate the absence of an underlying anatomical representation. The searches found no controlled evidence resolving that causal inference for the February 2024 model.
Caveats
- No decisive causal evidence item was found.
- The specific anatomical examples were not independently verified in usable primary records.
Evidence (0 items)
Nothing we found settles this yet.
How we judged it
- Kind of claim
- Causal claim
- Deadline
- None given. We don’t add one.
Where we had to interpret
- The claim attributes anatomical errors to an absence of internal anatomical representation, rather than merely reporting that errors occur.
- Underlying model includes learned representations; the wording does not restrict it to an explicitly programmed anatomical template.
- The target is the February 2024 research-preview snapshot, the latest publicly documented version before the post.
Right if: Version-matched evidence verifies anatomical errors and causally links them to the absence of anatomical representations, rather than merely showing that no explicit anatomy module was disclosed.
Wrong if: Controlled evidence shows that relevant anatomical representations exist and that the cited errors arise from another mechanism, undermining the asserted explanation.
We wrote this test after the outcome was known.
What would settle it
Verified examples from the original model and a controlled representation or intervention study showing whether absent anatomical structure causes those errors.
We found 4 claims in this post. See them all.
Full record
Source and dates
Marcus on AI, No, Sora has not “learned physics”, paragraph 9.
- Said
- We read the source
- live page, full text, public
- Evidence up to
- Checked
We read this wording on 2026-10-29. The post may have been edited after 2024-03-02.
Where it was said (1)
Said once in the posts we read.
: Marcus on AI, No, Sora has not “learned physics”
You also wind up with humans with six fingers, humans with three arms, weird walking gaits, ants with four legs, etc because there is no underlying model of the physiological structure of an ant or a human being.
- Where
- paragraph 9
- Published
- 2024-03-02
- We read it
- , live page
- Access
- full text, public
History
Versions
- Current: Unresolved. Evidence up to 2026-10-28.
What happened to this record
PublishedBy us
Published after both AI reviews and the final check passed.