โUnfortunately the key test was not done.โ
Our reading, the sentence that was checked:
The key test of o3's base model on ARC without pretraining was not done.
Assessment: Unresolved Evidence as of
Where and when Gary Marcus wrote it
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-c39-c129a4-a1
We recorded 17 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 2024-12-22. 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 releaseโs reference date)
From the speaker
- the โbase modelโ without the pretraining
- the key test was not done
Our interpretation
- Pretraining means ARC-specific training, not all training needed to produce a language model.
- The claim concerns the experiment underlying the December 20 demonstration, as discussed on December 22.
- The plain reading asserts that the experiment was not performed. Merely showing that no result was published would establish a narrower claim.
- Restricting the assertion to experiments performed by ARC Prize would materially change its evidential burden.
Counts as supported if: Experimental records or statements from the relevant investigators establish that the December o3 system was not evaluated without ARC-specific training before the post.
Counts as contradicted if: A dated experimental record establishes that the relevant ARC-untrained version was evaluated before the post, whether or not its results were public.
Retrospective: these criteria were written after the outcome was public.
Current assessment
Was it true for the period described?
Outcome: Unresolved
The record was checked, and the evidence available by the cutoff does not settle it.
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
The search did not establish whether OpenAI performed the requested experiment internally before publication. A missing public result and an unperformed experiment are different claims. Later testing of released o3 does not settle this historical question because that model differed from the December preview.
Limitations
- A narrower reading confined to ARC Prize's own evaluation would be easier to support.
- Private experimental records were unavailable.
Evidence (1 item)
Context only: ARC Prize Foundation,
differs from the o3-preview
Why it matters here: The later released model is different. Its evaluation cannot establish whether the requested experiment on the December system had already occurred.
- Publisher
- ARC Prize Foundation
- Kind of source
- Independent measurement
- Describes events of
- Public from
What would settle it
A dated statement or experimental record from OpenAI and ARC Prize identifying whether the December system was evaluated without ARC-specific training before December 22.
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, ๐ผ๐ฏ โ๐๐ฅ๐ ๐๐๐โ ๐ฝ๐ผ๐๐๐บ๐ผ๐ฟ๐๐ฒ๐บ ๐บ๐ฒ๐ด๐ฎ๐๐ต๐ฟ๐ฒ๐ฎ๐ฑ: ๐๐ต๐ ๐๐ต๐ถ๐ป๐ด๐ ๐ด๐ผ๐ ๐ต๐ฒ๐ฎ๐๐ฒ๐ฑ, ๐๐ต๐ฎ๐ ๐๐ฒ๐ป๐ ๐๐ฟ๐ผ๐ป๐ด, ๐ฎ๐ป๐ฑ ๐๐ต๐ฎ๐ ๐ถ๐ ๐ฎ๐น๐น ๐บ๐ฒ๐ฎ๐ป๐
Unfortunately the key test was not done.
- Where
- paragraph 9
- Published
- 2024-12-22
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-c39-c129a4-a1: Current. Outcome: Unresolved. 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.