“And, sorry Sam, when you actually look at the data. humans are still ahead.”
Our reading, the sentence that was checked:
When you actually look at the data in the cited Turing Test study, humans are still ahead of the AI systems tested.
Assessment: Supported Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Nope, the Turing Test has not been solved, paragraph 4.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-nope-the-turing-test-has-not-been-e5d345-a1
We recorded 4 claims from this post. See every claim from this post.
The wording above is the version this site observed on 2026-10-29. The source may have been edited after 2023-12-09. 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 release’s reference date)
Conditions
- when you actually look at the data in the cited study (qualifier, stated by the speaker)
- the AI systems tested in that study (scope, stated by the speaker)
From the speaker
- when you actually look at the data
- humans are still ahead
Our interpretation
- The surrounding citation limits this comparison to the AI witnesses tested in Jones and Bergen's experiment.
- Ahead means a higher overall judged-human rate, not superior performance on every intellectual task.
- Use the paper version public on December 9, 2023.
- The target period is the 2023 experiment reported in the cited paper; exact collection dates are unspecified.
Counts as supported if: Human witnesses have a higher overall judged-human rate than every tested AI witness configuration.
Counts as contradicted if: At least one tested AI witness configuration matches or exceeds the human witnesses' overall judged-human rate.
Retrospective: these criteria were written after the outcome was public.
Current assessment
Was it true for the period described?
Outcome: Supported
The dated evidence matches what the claim committed to, under the criteria frozen before grading.
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
Human witnesses scored 63%, above the strongest tested AI configuration at 41%. The statement accurately describes the cited study's results.
Limitations
- The finding concerns this experiment and its prompts.
- It does not establish that every possible AI configuration would perform below humans.
Evidence (1 item)
Supports the claim: arXiv; Cameron Jones and Benjamin Bergen,
Human witnesses performed best, with an SR of 63% (see Figure 4).
Why it matters here: The section reports a 63% human success rate and 41% for the strongest GPT-4 prompt. All other tested AI configurations scored lower.
- Publisher
- arXiv; Cameron Jones and Benjamin Bergen
- Kind of source
- Preprint, not peer reviewed
- Describes events of
- Public from
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Nope, the Turing Test has not been solved
And, sorry Sam, when you actually look at the data. humans are still ahead.
- Where
- paragraph 4
- Published
- 2023-12-09
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-nope-the-turing-test-has-not-been-e5d345-a1: Current. Outcome: Supported. 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.
About assessment marcus-nope-the-turing-test-has-not-been-e5d345-a1.