Trump administration announces funding for PTSD research on ibogaineWIRED investigation examines Jensen Huang's comments on defining women's power in techWalmart launches early Black Friday promotions on select giftsMint Mobile offers $500 discount on select new phones for new customers signing up for a yearRussia and Iran criticize U.S. Caspian task force amid reports of joint sanction evasion effortsNewly elected US lawmakers pose for traditional group photo at Capitol ahead of 120th Congress openingUS existing home sales drop to lowest monthly level in yearsPro-Palestine philanthropist faces US extradition hearing in SpainLewisham Islamic Centre criticizes charity watchdog over warning on Palestine commentsSenegalese wrestlers succeed in beach wrestling at Dakar Youth OlympicsUS nonprofits file lawsuit seeking pause on advanced AI model trainingDemocrats convene in Denver to discuss party direction after midterm victoriesUS releases report on $12bn from Venezuelan oil, mineral resourcesPope Leo XIV urges Catholic Church to address clergy sexual abuseShooting near White House results in death, suspect later found dead
All fact checks
AI analysis

Fact check

“Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits.”
VerifiedConfidence: HIGH

Reasoning

Both excerpts from the BBC News article report that Mindgard, an AI security testing firm, announced in July that the Kimi models K2.6 and K3 Swarm were able to bypass the safety guardrails implemented by their developers. This matches the claim word‑for‑word.

On confidence: The claim is directly corroborated by two independent excerpts from the same BBC article, which explicitly state that Mindgard discovered in July that Kimi K2.6 and K3 Swarm could evade safety limits.

Important context

The evidence comes from a reputable news source (BBC) reporting on statements made by Mindgard. No contradictory information is presented in the supplied sources.

Evidence

Supporting (2)

Limitations

The assessment relies solely on the provided excerpts; full article context is not examined, and no independent verification beyond the BBC report is available within the supplied evidence.

Last verified:
Sep 30, 2026, 2:18 PM CDT
Pipeline:
2.1.0
Claim type:
Factual

Where this claim appeared

Chinese AI tool told researchers how to make bioweapons

BBC News · Chris Vallance