“ChatGPT tended not to do this kind of stuff (unless you used “jailbreaking” techniques to try to trick it), whereas from what I can tell, Bing went off the rails really fast.”
Our reading:
From what Marcus can tell, Bing's chatbot went off the rails really fast, whereas ChatGPT tended not to behave this way unless users used jailbreaking techniques to trick it.
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 explicitly qualifies the comparison with 'from what I can tell' and describes ChatGPT with 'tended not to.' The supplied policy does not allow the plain-reading exception for this hedged claim. Scoring a firm comparison would require adding a testing standard and strengthening his commitment. This decision does not establish whether the reported behavioral contrast was accurate.
Caveats
- No factual verdict is proposed on the systems' February 2023 behavior.
- Outcome-known status is false because no scoreable outcome is defined, not because an empirical outcome remains pending.
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
- from what I can tell (their words)
- unless you used jailbreaking techniques (ChatGPT) (their words)
Where we had to interpret
- Marcus presents a qualified impression of the two systems' behavior, explicitly limiting the Bing assessment to what he can tell.
- The surrounding examples explain the kinds of behavior he means, but do not establish a comparative frequency or testing standard.
- Under the supplied policy, the epistemic qualification prevents using the plain-reading exception to turn this impression into a firm comparative claim.
We don’t grade claims like this. We only check the quote and who said it.
We found 14 claims in this post. See them all.
Full record
Source and dates
Marcus on AI, Why *is* Bing so reckless?, paragraph 7.
- Said
- We read the source
- live page, full text, public
- Evidence up to
- Checked
We read this wording on 2026-10-29. The post may have been edited after 2023-02-20.
Where it was said (1)
Said once in the posts we read.
: Marcus on AI, Why *is* Bing so reckless?
ChatGPT tended not to do this kind of stuff (unless you used “jailbreaking” techniques to try to trick it), whereas from what I can tell, Bing went off the rails really fast.
- Where
- paragraph 7
- Published
- 2023-02-20
- 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.