“Remember how we were told in 2023 that hallucinations would be solved in a matter of months? They are still here.”
Our reading, the sentence that was checked:
Despite 2023 promises that hallucinations would soon be solved, they persist as of May 2025.
Assessment: Supported Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, The “AI 2027” Scenario: How realistic is it?, paragraph 23.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-the-ai-2027-scenario-how-realistic-cc179c-a1
We recorded 29 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 2025-05-22. 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 release’s reference date)
From the speaker
- we were told in 2023 that hallucinations would be solved in a matter of months
- They are still here
Our interpretation
- The checkable core is that as of the post (May 2025), leading LLMs still hallucinated at meaningful rates. The 2023 promise is background and is checked as context.
- Target period: the most recent period before the post that public evidence covers, April 2025 to the post date, when frontier model evaluations were published.
Counts as supported if: Credible measurements or reports from around April–May 2025 show leading LLMs still producing hallucinations at non-trivial rates.
Counts as contradicted if: Evidence that by May 2025 leading LLMs had essentially eliminated hallucinations.
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
The checkable core is that hallucinations were still present in May 2025. OpenAI's April 2025 system card for its newest models reports hallucination rates of 33% for o3 and 48% for o4-mini on its PersonQA test. Both are higher than the older o1's 16%, and OpenAI says more research is needed to understand why. That is clear evidence that hallucinations persisted a month before the post. As background, Reid Hoffman said in September 2023 that hallucinations could be brought to human-expert levels 'within months'. A prediction market on that claim resolved NO.
Limitations
- Relies mainly on one developer's internal benchmarks.
- The 2023 promise is documented via a secondary page.
Evidence (2 items)
Supports the claim: OpenAI,
PersonQA accuracy (higher is better) 0.59 0.36 0.47 hallucination rate (lower is better) 0.33 0.48 0.16
Why it matters here: OpenAI's newest reasoning models in April 2025 hallucinated on 33% (o3) and 48% (o4-mini) of PersonQA questions, higher than the older o1. Hallucinations were plainly still present a month before the post.
- Publisher
- OpenAI
- Kind of source
- Company disclosure: the company describing itself, not an independent finding
- Describes events of
- Public from
Context only: Manifold Markets (Zvi Mowshowitz),
I would bet you any sum of money you can get the hallucinations right down into the line of human-expert rate within months.
Why it matters here: Documents a prominent 2023 claim that hallucinations could be brought to expert levels within months, matching Marcus's background premise. The market resolved NO. The available_at date is the resolution date because the creation date is not shown.
- Publisher
- Manifold Markets (Zvi Mowshowitz)
- Kind of source
- Secondary summary
- Describes events of
- Public from
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, The “AI 2027” Scenario: How realistic is it?
Remember how we were told in 2023 that hallucinations would be solved in a matter of months? They are still here.
- Where
- paragraph 23
- Published
- 2025-05-22
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-the-ai-2027-scenario-how-realistic-cc179c-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-the-ai-2027-scenario-how-realistic-cc179c-a1.