Fact check
“OpenAI constrained access to the model that led to the hacks, didn’t disclose the company’s safety and security practices, limited the length of the investigation, and had ultimate say over what the researchers could publish.”
Reasoning
The supplied source directly reports that OpenAI constrained model access leading to hacks, withheld safety and security details, limited the investigation's scope, and retained final editorial control over researchers' publications. No contradictory evidence is provided.
On confidence: Multiple excerpts from a MIT Technology Review article explicitly state that OpenAI constrained access, did not disclose safety practices, limited investigation length, and controlled publication.
Important context
The claim pertains to OpenAI's handling of a specific AI agent hack incident as described in the MIT Technology Review article.
Evidence
Supporting (3)
- Tier 1 — Primary sourceWho’s liable when AI agents go rogue? | MIT Technology Review
board that the agents had created, they could’ve promptly escalated their findings to security and safety teams. And the company could’ve better designed its sandbox to ensure that agents couldn’t access the internet. But even if OpenAI…
- Tier 1 — Primary sourceWho’s liable when AI agents go rogue? | MIT Technology Review
more damaging incident where AI agents bypass sandboxes to access systems they shouldn’t. So the big question is: How do we hold companies liable when they lose control of their AI agents? Reporting OpenAI didn’t disclose the German wiki…
- Tier 1 — Primary sourceWho’s liable when AI agents go rogue? | MIT Technology Review
hacks, didn’t disclose the company’s safety and security practices, limited the length of the investigation, and had ultimate say over what the researchers could publish. We still don’t know what set the attack in motion back in May and…
Limitations
The assessment relies on a single source; additional independent verification would strengthen the conclusion. No independent origin corroborated this claim, so it cannot be verified and confidence cannot be high.
- Last verified:
- Sep 30, 2026, 7:48 PM CDT
- Pipeline:
- 2.1.0
- Claim type:
- Factual
Where this claim appeared
Who’s liable when AI agents go rogue?MIT Technology Review · Michelle Kim