“It’s notorious for making illegal moves in chess.”
Our reading, the sentence that was checked:
ChatGPT is notorious for making illegal moves in chess.
Assessment: Supported Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, Could GPT-5 revolutionize military strategy?, paragraph 3.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-could-gpt-5-revolutionize-military-f7c3fb-a1
We recorded 8 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 2024-02-07. 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
- ChatGPT
- notorious
- making illegal moves in chess
Our interpretation
- The ordinary reading is that illegal moves were a repeatedly documented and publicly recognized weakness, not that every game contained them.
- The target period covers ChatGPT's public history through the post. Notoriety concerns accumulated reports rather than one reporting quarter.
- Different ChatGPT models and prompts must be distinguished.
Counts as supported if: Contemporaneous tests document repeated illegal moves, and public coverage establishes that the problem was recognized.
Counts as contradicted if: Representative contemporary records establish that the alleged pattern or public reputation was substantially mistaken.
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
Repeated illegal moves were documented experimentally and discussed publicly before the post. Successful games under other prompts do not negate that reputation. The evidence supports a recognized weakness, not an assertion that ChatGPT always makes illegal moves.
Limitations
- Notoriety is qualitative.
- Failure rates depend on model version and prompting.
- The public-coverage evidence is secondary reporting; the experimental evidence is primary.
Evidence (3 items)
Supports the claim: arXiv; Mu-Tien Kuo, Chih-Chung Hsueh and Richard Tzong-Han Tsai,
only 1.59% of games concluded naturally
Why it matters here: The researchers tested gpt-3.5-turbo-0301 across 3,200 games. Their procedure terminated games after ten consecutive illegal attempts, and their results document persistent rule-following failures.
- Publisher
- arXiv; Mu-Tien Kuo, Chih-Chung Hsueh and Richard Tzong-Han Tsai
- Kind of source
- Preprint, not peer reviewed
- Describes events of
- Public from
Supports the claim: Innovation Origins, archived by IO+,
following strict rules
Why it matters here: This contemporary article discusses separate public demonstrations involving illegal moves. It supports the reputation component; its humorous wording is not treated as a technical explanation.
- Publisher
- Innovation Origins, archived by IO+
- Kind of source
- News report
- Describes events of
- Public from
Context only: Dmitri Brereton, DKB Blog,
fully legal
Why it matters here: A 19-game GPT-3.5 experiment reported successful legal play when the complete move sequence was supplied each turn. It also acknowledged occasional illegal moves, so it limits generalization without disproving the documented reputation.
- Where
- Method
- Publisher
- Dmitri Brereton, DKB Blog
- Kind of source
- Independent measurement
- Describes events of
- Public from
Where it was said (1)
Said once in the sources this register covers.
: Marcus on AI, Could GPT-5 revolutionize military strategy?
It’s notorious for making illegal moves in chess.
- Where
- paragraph 3
- Published
- 2024-02-07
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-could-gpt-5-revolutionize-military-f7c3fb-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-could-gpt-5-revolutionize-military-f7c3fb-a1.