“Without a proper model, you can’t possibly reliably reason about time, and affiliated concepts like inflation and changing prices. A model might be able to answer queries about time, but only superficially.”
Our reading:
Without a proper world model, an AI system cannot reliably reason about time, inflation, or changing prices, only superficially.
Assessment: Can’t be checked
What happened
Not graded on evidence
Outcome: Can’t be checked
An opinion, a recommendation, or too vague to test. Listed, not scored.
Evidence up to . Checked .
Why
In the 2025-08-12 post, Marcus says that without a proper model, a system cannot reliably reason about time, inflation or changing prices, and can answer time questions only superficially. The quoted passage does not say what counts as a proper model. It sets no threshold for 'reliably' or 'superficially'. The evidence search did not find an agreed test of whether a system has a proper world model. It also found no benchmark that links reasoning about inflation or changing prices to whether a system has a world model. The search screened two sources: a temporal-reasoning benchmark in the NeurIPS 2025 Datasets and Benchmarks track, and a chronology preprint (arXiv 2511.14214). Neither sorts systems by whether they have a world model, so neither was used. With no definition and no evidence items, the claim cannot be scored as stated.
Caveats
- The case contains no evidence items, so no system's performance was scored.
- The two screened sources measure temporal reasoning or chronology. Neither tests whether a world model is needed for reliable reasoning.
- The search found no benchmark that links reasoning about inflation or changing prices to whether a system has a world model. The case does not show whether other research on price reasoning exists.
- The quoted passage does not define a proper model, so the case does not settle what would count as one.
Evidence (0 items)
Claims like this aren’t scored, so there is no evidence to show.
How we judged it
- Kind of claim
- Causal claim
- Deadline
- None given. We don’t add one.
Conditions
- without a proper world model (their words)
Where we had to interpret
- This is a claim about necessity: reliable temporal and price reasoning requires a 'proper' world model.
- Marcus does not define a 'proper model', and no public test separates systems that have one from systems that lack one. Without that line, the claim cannot be tested.
- 'Reliably' and 'superficially' come with no threshold.
We don’t grade claims like this. We only check the quote and who said it.
We found 12 claims in this post. See them all.
Full record
Source and dates
Marcus on AI, LLMs are not like you and me—and never will be., paragraph 28.
- Said
- We read the source
- live page, full text, public
- Evidence up to
- Checked
We read this wording on 2026-10-28. The post may have been edited after 2025-08-12.
Where it was said (1)
Said once in the posts we read.
: Marcus on AI, LLMs are not like you and me—and never will be.
Without a proper model, you can’t possibly reliably reason about time, and affiliated concepts like inflation and changing prices. A model might be able to answer queries about time, but only superficially.
- Where
- paragraph 28
- Published
- 2025-08-12
- We read it
- , live page
- Access
- full text, public
History
Versions
- Current: Can’t be checked. Evidence up to 2026-10-28.
What happened to this record
PublishedBy us
Published after both AI reviews and the final check passed.
Held backBy us
The final check failed: the write-up said more than the evidence showed.