“I am pretty sure this kind of failure would be easy to replicate.”
Our reading:
Imagen's failures on compositional block-stacking prompts would likely be easy to replicate.
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 said he was 'pretty sure' the failure would be easy to replicate. The supplied policy excludes hedged statements from scoring. Treating this as a firm forecast would also require inventing a standard for 'easy'. Later tests could document similar failures, but would not justify those additions to his words. No outcome evidence was sought because the statement fails the scoring criteria before evidence assessment.
Caveats
- This assessment does not establish whether Imagen's compositional failures were reproducible.
Evidence (0 items)
Claims like this aren’t scored, so there is no evidence to show.
How we judged it
- Kind of claim
- Forecast
- Deadline
- None given. We don’t add one.
Where we had to interpret
- The context connects 'this kind of failure' to Imagen's omitted block and incorrect shape in the described block-stacking image.
- Marcus expresses a hedged expectation. He does not specify a replication procedure or a standard for 'easy'. Under the supplied policy, this is not scored as a firm forecast.
We don’t grade claims like this. We only check the quote and who said it.
We found 14 claims in this post. See them all.
Full record
Source and dates
Marcus on AI, Horse rides astronaut, paragraph 99.
- 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 2022-05-28.
Where it was said (1)
Said once in the posts we read.
: Marcus on AI, Horse rides astronaut
I am pretty sure this kind of failure would be easy to replicate.
- Where
- paragraph 99
- Published
- 2022-05-28
- 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.