“From what I can recall watching the demo, I saw zero evidence that o3 could work reliably in open-ended domains.”
Our reading:
From what Marcus can recall of watching the o3 demo, he saw zero evidence that o3 could work reliably in open-ended domains.
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
Marcus qualified this as a report of what he recalls seeing. The recording could show whether OpenAI presented relevant evidence, but it could not establish what he noticed or remembered. Scoring presentation content would remove his qualification and assess a different proposition. The claim therefore cannot be fairly graded as worded.
Caveats
- This decision makes no finding about the demo's contents or o3's reliability.
Evidence (0 items)
Claims like this aren’t scored, so there is no evidence to show.
How we judged it
- Kind of claim
- Observation
- Deadline
- None given. We don’t add one.
Conditions
- from what I can recall (their words)
- in the o3 demo he watched (their words)
Where we had to interpret
- The statement reports what Marcus recalls perceiving in the demo. Its qualification is part of the claim.
- A recording could establish what OpenAI presented. Treating that as a test of what Marcus recalls seeing would substitute a different claim.
- The statement does not require an evaluation establishing reliability; its wording concerns whether he saw any evidence of reliability.
We don’t grade claims like this. We only check the quote and who said it.
What would settle it
A separately stated, externally checkable claim about what the demo presented could be assessed against its recording and accompanying materials. That would be a different claim.
We found 18 claims in this post. See them all.
Full record
Source and dates
Marcus on AI, o3, AGI, the art of the demo, and what you can expect in 2025, paragraph 12.
- 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 2024-12-21.
Where it was said (1)
Said once in the posts we read.
: Marcus on AI, o3, AGI, the art of the demo, and what you can expect in 2025
From what I can recall watching the demo, I saw zero evidence that o3 could work reliably in open-ended domains.
- Where
- paragraph 12
- Published
- 2024-12-21
- 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
A reviewer said our test wasn’t fair to what was actually said.