“This list is probably not exhaustive and will continue to grow.”
Our reading, the sentence that was checked:
The list of OpenAI/LLM security issues will continue to grow.
Assessment: Supported Settled before its deadline on 2026-10-29 Evidence as of
Where and when Gary Marcus wrote it
Marcus on AI, What Could Possibly Go Wrong with Sam Altman’s New Ambitions?, paragraph 14.
- Said
- Source observed
- live page, full text, public
- Evidence as of
- the cutoff for this assessment
- Assessment recorded
- assessment marcus-what-could-possibly-go-wrong-with-619211-a1
We recorded 23 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 2024-02-09. 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
- This list is probably not exhaustive
- will continue to grow
Our interpretation
- The firm forecast concerns additional publicly documented OpenAI or LLM security issues after February 9, 2024.
- At least one distinct additional vulnerability or incident establishes growth. A new exploit involving a later feature counts even if it belongs to an already known attack class.
- A demonstrated vulnerability counts without evidence of criminal exploitation.
- The tentative statement about existing omissions is not a separate firm commitment.
Counts as supported if: A reliable public disclosure after February 9, 2024 documents at least one additional distinct OpenAI or LLM security vulnerability or incident.
Counts as contradicted if: Without a deadline, a finite period containing no additional disclosures cannot establish failure.
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
Tenable's March 24, 2025 advisory publicly documented an additional ChatGPT Search vulnerability involving memory injection and extraction. This satisfies the stated early-resolution rule: the list gained a distinct security issue after Marcus's post. No deadline needs to be invented, and proof of criminal exploitation is unnecessary.
Limitations
- This establishes additional vulnerability disclosure, not a rate of future incidents.
- It does not establish that attackers exploited the issue against real victims.
- The disclosure does not determine the product's security status at the evaluation date.
Evidence (1 item)
Supports the claim: Tenable,
memories could be both injected and exfiltrated.
Why it matters here: Tenable publicly disclosed a ChatGPT Search attack that bypassed isolation to inject and extract memories. The disclosure adds a distinct product-specific issue to the earlier list; the event dated here is public disclosure, following private reporting in December 2024.
- Publisher
- Tenable
- 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, What Could Possibly Go Wrong with Sam Altman’s New Ambitions?
This list is probably not exhaustive and will continue to grow.
- Where
- paragraph 14
- Published
- 2024-02-09
- Source observed
- , live page
- Access
- full text, public
History
Assessment versions
- Assessment marcus-what-could-possibly-go-wrong-with-619211-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-could-possibly-go-wrong-with-619211-a1.