“So now GPT 4.5 has dropped, and — breaking news — I was right. Hallucinations didn’t disappear today, and nor did stupid errors.”
Our reading, the sentence that was checked:
GPT-4.5 did not eliminate hallucinations or stupid errors.
Assessment: Supported Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Hot take: GPT 4.5 is a nothing burger, paragraph 8.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-hot-take-gpt-45-is-a-nothing-burger-e8dbb7-a1
We recorded 7 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 2025-02-27. 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
- GPT 4.5 has dropped
- Hallucinations didn’t disappear today
- nor did stupid errors
Our interpretation
- Assess the model released on February 27, 2025.
- The ordinary reading is that fabricated factual answers and obvious mistakes persisted. It does not imply that their frequency failed to improve.
- Treat incorrect answers to questions whose answers are explicitly supplied as an ordinary example of an obvious mistake.
Counts as supported if: Launch-model evaluations establish both nonzero hallucinations and errors on straightforward tasks.
Counts as contradicted if: Reliable evidence establishes that the released model eliminated either claimed class of failure. Improved scores alone do not contradict persistence.
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
OpenAI's launch evaluations show hallucinations and incorrect answers even when the necessary information is supplied. That supports the narrow claim that these failures persisted. The same results show improvement, so this finding does not establish that GPT-4.5 was useless or that scaling had stopped working.
Limitations
- The evidence is developer-reported.
- The benchmarks establish persistence, not the frequency of failures in ordinary use.
- Stupid errors has no formal definition.
Evidence (1 item)
Supports the claim: OpenAI,
We tested OpenAI GPT-4.5 against PersonQA, an evaluation that aims to elicit hallucinations.
Why it matters here: The launch card reports a 0.19 PersonQA hallucination rate and 0.74 accuracy on unambiguous BBQ questions, where the answer is supplied in the prompt. These establish persistent hallucinations and straightforward answer-selection mistakes, although PersonQA improved over GPT-4o.
- Publisher
- OpenAI
- Kind of source
- Company disclosure: the company describing itself, not an independent finding
- Describes events of
- Public from
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Hot take: GPT 4.5 is a nothing burger
So now GPT 4.5 has dropped, and — breaking news — I was right. Hallucinations didn’t disappear today, and nor did stupid errors.
- Where
- paragraph 8
- Published
- 2025-02-27
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-hot-take-gpt-45-is-a-nothing-burger-e8dbb7-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-hot-take-gpt-45-is-a-nothing-burger-e8dbb7-a1.