“Some of its advice will be head-scratchingly bad.”
Our reading, the sentence that was checked:
Some of GPT-4's advice will be very bad.
Assessment: Supported Settled before its deadline on 2026-10-29 Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, What to Expect When You’re Expecting … GPT-4, prediction 6 of 7.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-what-to-expect-when-youre-expecting-c9e809-a1
We recorded 21 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 2022-12-25. This page does not claim the wording was captured then.
What the claim commits to
- Kind
- Forecast
- Deadline, as the speaker wrote it
- None stated. This site does not add one.
- Deadline state when assessed
- Settled before its deadline
- Deadline state on 2026-10-29
- Settled before its deadline (the release’s reference date)
From the speaker
- Some of its advice
- will be
- head-scratchingly bad
Our interpretation
- The target is advice generated by released GPT-4.
- The plain reading is that at least some recommendations will be substantively and seriously wrong or potentially harmful under established factual or safety standards.
- The phrase does not require showing that most advice is bad or that someone acted on it.
- No deadline is supplied.
Counts as supported if: A documented GPT-4 recommendation is assessed as seriously erroneous or potentially harmful against established standards by qualified evaluators.
Counts as contradicted if: A decisive demonstration rules out qualifying bad advice within the claimed scope. A finite sample of good advice alone cannot refute this unrestricted existential forecast.
Retrospective: these criteria were written after the outcome was public.
Current assessment
Did the forecast come true?
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
- Settled before its deadline
- Assessment recorded
- Policy version
- 2026-10-28.7
Rationale
A primary clinical study documents GPT-4 antibiotic recommendations that expert reviewers classified as harmful against clinical standards. That satisfies the ordinary meaning of some very bad advice. Other recommendations were optimal, which does not contradict this limited existential claim.
Limitations
- The study concerns a particular infectious-disease setting and does not measure all GPT-4 advice.
- Potential harm was assessed; actual patient injury was not established.
- The readable primary record is the study abstract, not the complete case-level dataset.
- The event is dated only to 2023; the availability date conservatively uses the record's 2024 issue date.
Evidence (1 item)
Supports the claim: Clinical Infectious Diseases; abstract hosted by PubMed,
harmful in 2 (5%)
Why it matters here: Two infectious-disease physicians assessed GPT-4 management recommendations against clinical literature and guidelines and identified harmful antibiotic advice. The same evaluation found optimal antibiotic recommendations in other cases, so it supports some bad advice without establishing universal failure.
- Where
- Abstract, Results
- Publisher
- Clinical Infectious Diseases; abstract hosted by PubMed
- Kind of source
- Peer-reviewed paper
- Describes events of
- Public from
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, What to Expect When You’re Expecting … GPT-4
Some of its advice will be head-scratchingly bad.
- Where
- prediction 6 of 7
- Published
- 2022-12-25
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-what-to-expect-when-youre-expecting-c9e809-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-what-to-expect-when-youre-expecting-c9e809-a1.