“(Systems like Gemini can do this a little, but often hallucinate heavily, and don’t think as yet they can take in a full Simpsons episode, let alone follow 4 seasons of Succession and explain who is lying to whom and to what end in real time.)”
Our reading:
Systems like Gemini can do the comprehension challenge a little but often hallucinate heavily, and he does not think they can yet take in a full Simpsons episode, let alone follow four seasons of Succession and explain in real time who is lying to whom and to what end.
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’s April 2, 2025 capability assessment is explicitly tentative: he says he does not think systems can perform the described tasks yet [marcus-ai-has-sort-of-passed-the-turing-840ee7-o1]. His more direct assertion that systems “often hallucinate heavily” lacks a defined task scope, frequency, or severity threshold, leaving no sufficiently specified proposition to score [marcus-ai-has-sort-of-passed-the-turing-840ee7-o1].
Caveats
- The packet contains no external capability evidence.
- This assessment does not establish Gemini’s actual comprehension abilities or hallucination rates as of April 2, 2025.
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
- he doesn't think, as yet (their words)
- systems like Gemini (their words)
Where we had to interpret
- The passage concerns systems available when the post appeared on April 2, 2025.
- The episode and series capability assessment is explicitly tentative: Marcus says he does not think systems can do these things yet. This does not commit him to a categorical claim of incapability.
- In context, taking in an episode concerns comprehension, but the passage supplies no required accuracy, hallucination frequency, or response latency.
- The assertion that systems often hallucinate heavily is more direct, but the passage does not specify the tasks, frequency, or severity needed to score it separately. Adding these would materially change the assessment.
We don’t grade claims like this. We only check the quote and who said it.
We found 10 claims in this post. See them all.
Full record
Source and dates
Marcus on AI, AI has (sort of) passed the Turing Test; here’s why that hardly matters, paragraph 30.
- 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 2025-04-02.
Where it was said (1)
Said once in the posts we read.
: Marcus on AI, AI has (sort of) passed the Turing Test; here’s why that hardly matters
(Systems like Gemini can do this a little, but often hallucinate heavily, and don’t think as yet they can take in a full Simpsons episode, let alone follow 4 seasons of Succession and explain who is lying to whom and to what end in real time.)
- Where
- paragraph 30
- Published
- 2025-04-02
- 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.