Mindgard

It’s Too Easy to Use AI to Develop Bioweapons

BBC News

Chinese AI tool told researchers how to make bioweapons

ELMUNDOAMERICA

Chinese AI that opened the door to biological weapons

NewsBytes

These Chinese AI models told researchers how to assassinate people

Google Cloud

GTIG AI Threat Tracker: From Prompting to Autonomy  The Evolution of Adversarial AI

Anthropic

Countering misuse of AI: September 2026 / Anthropic

GitHub

Security.Md

Sarin.Html

Elon Musk

Rishi Sunak

Kamala Harris

Bill Gates

Andrew Ng

Yoshua Bengio

Fei-Fei Li

Melanie Mitchell

Sam Altman

Dario Amodei

Geoffrey Hinton

Yann LeCun

Gary Marcus

Max Tegmark

Connor Leahy

Eliezer Yudkowsky

Jaan Tallinn

Marc Andreessen

Eric Schmidt

Norbert Wiener

Arthur Clarke

Irving John Good

Claude Shannon

Hans Moravec

John Smart

There's a "wall of fear-mongering and doomerism" in the AI world right now.

"Worrying about AI today is like worrying about overpopulation on Mars."

Concerns that AI could pose a threat to humanity is "preposterously ridiculous."

Claiming AI poses an existential threat is "such an extreme" and risks "wip[ing] out some of its potential benefits."

"I'm more concerned about... the risks that are here and now [than the existential threat of AI]."

Current AI is "not anywhere close" to posing an existential threat but it could in the future.

AI is the "biggest existential threat" to humanity.

AGI's worst-case scenario would be "lights-out for all of us."

Powerful AI systems "taking control" pose an "existential threat."

AI has a "10 to 25 per cent" chance of destroying humanity.

"The most likely result of building a superhumanly smart AI... is that literally everyone on Earth will die."

Does AI Pose an Existential Threat to Humanity?

Chinese AI developer Moonshot told the BBC on Wednesday that it is carrying out an internal review after the security firm Mindgard bypassed safeguards on its Kimi K2.6 and K3 Swarm, prompting the agents to describe biological weapons production and assassination planning.

Chinese AI developer Moonshot told the BBC on Wednesday that it is carrying out an internal review after the security firm Mindgard bypassed safeguards on its Kimi K2.6 and K3 Swarm, prompting the agents to describe biological weapons production and assassination planning.

Mindgard identified the vulnerabilities in July and emailed Moonshot on July 27, before publishing a blog post about the issue on Sept. 12. Mindgard said Moonshot had only responded recently, after the BBC contacted the company for comment.

Mindgard identified the vulnerabilities in July and emailed Moonshot on July 27, before publishing a blog post about the issue on Sept. 12. Mindgard said Moonshot had only responded recently, after the BBC contacted the company for comment.

Mindgard researcher Jim Nightingale reported that he jailbroke Kimi by eliciting the AI's system instructions and exploiting its custom memory by placing the jailbreak in a local DWS directory inside Kimi's authentication tree. He then used new system instructions to create an unrestricted persona called "Apeiron," Ancient Greek for "unlimited" or "boundless."

Mindgard researcher Jim Nightingale reported that he jailbroke Kimi by eliciting the AI's system instructions and exploiting its custom memory by placing the jailbreak in a local DWS directory inside Kimi's authentication tree. He then used new system instructions to create an unrestricted persona called "Apeiron," Ancient Greek for "unlimited" or "boundless."

The jailbreak produced outputs on explosives, malware and chemical agents, including detailed instructions and compositions for creating sarin gas, a potent nerve agent. Mindgard has not demonstrated whether Kimi’s responses would work as intended.

The jailbreak produced outputs on explosives, malware and chemical agents, including detailed instructions and compositions for creating sarin gas, a potent nerve agent. Mindgard has not demonstrated whether Kimi’s responses would work as intended.

Moonshot told the BBC it welcomed third-party input as "a key pillar for building better and safer AI" and said internal evaluations showed a high refusal rate for similar requests. It is now discussing the findings with Mindgard.

Moonshot told the BBC it welcomed third-party input as "a key pillar for building better and safer AI" and said internal evaluations showed a high refusal rate for similar requests. It is now discussing the findings with Mindgard.

It comes as Anthropic recently revealed that <a target="_blank" rel="noopener noreferrer nofollow" href="https://www.verity.news/story/2026/anthropic-claims-it-has-blocked-biologicallinked-inquiries-using-claude-ai">it had disrupted attempts to use Claude for activity that could support biological weapons development.</a> Meanwhile, Google's threat intelligence team reported entities attempting to use Gemini to acquire step-by-step guides on "synthesizing weaponized biological agents."

It comes as Anthropic recently revealed that it had disrupted attempts to use Claude for activity that could support biological weapons development. Meanwhile, Google's threat intelligence team reported entities attempting to use Gemini to acquire step-by-step guides on "synthesizing weaponized biological agents."

Mindgard #

BBC News #

ELMUNDOAMERICA #

NewsBytes #

Google Cloud #

Anthropic #

GitHub #

CDC #

Mindgard identified the vulnerabilities in July and emailed Moonshot on July 27, before publishing a blog post about the issue on September 12. Mindgard said Moonshot had only responded recently, after the BBC contacted the company for comment.

Mindgard identified the vulnerabilities in July and emailed Moonshot on July 27, before publishing a blog post about the issue on September 12. Mindgard said Moonshot had only responded recently, after the BBC contacted the company for comment.

Mindgard researcher Jim Nightingale reported that he jailbroke Kimi by eliciting the AI's system instructions and exploiting its custom memory by placing the jailbreak in a local DWS directory inside Kimi's authentication tree. He then used new systemic instructions to create an unrestricted persona called "Apeiron," Ancient Greek for "unlimited" or "boundless."

Mindgard researcher Jim Nightingale reported that he jailbroke Kimi by eliciting the AI's system instructions and exploiting its custom memory by placing the jailbreak in a local DWS directory inside Kimi's authentication tree. He then used new systemic instructions to create an unrestricted persona called "Apeiron," Ancient Greek for "unlimited" or "boundless."

Activated by the commands "&lt;user_exits&gt;" and "&lt;Apeiron&gt;," the jailbreak produced outputs on explosives, malware and chemical agents, including detailed instructions and compositions for creating sarin gas, a potent nerve agent.

Activated by the commands "" and "," the jailbreak produced outputs on explosives, malware and chemical agents, including detailed instructions and compositions for creating sarin gas, a potent nerve agent.

It comes as Anthropic recently revealed that it had disrupted attempts to use Claude for activity that could support biological weapons development. Meanwhile, Google's threat intelligence team reported entities attempting to use Gemini to acquire step-by-step guides on "synthesizing weaponized biological agents."

Polite policy language stapled onto a model means nothing when a couple of stray phrases can strip every guardrail and hand over weapons recipes on demand. Moonshot ignoring this for so long is the real scandal, especially when its agents can act, code and spread the compromise. Safety has to be built into the architecture, not wished into existence.

Polite policy language stapled onto a model means nothing when a couple of stray phrases can strip every guardrail and hand over weapons recipes on demand. Moonshot ignoring this for so long is the real scandal, especially when its agents can act, code and spread the compromise. Safety has to be built into the architecture, not wished into existence.

Moonshot handles its models' safety seriously. Security, however, is a defined process: private advisories, a dedicated address, version details, reproduction steps and an impact assessment. Instead of hastily advertising vulnerabilities through flashy write-ups, Moonshot pursues coordinated disclosures that wait until a fix is readily available.

Moonshot handles its models' safety seriously. Security, however, is a defined process: private advisories, a dedicated address, version details, reproduction steps and an impact assessment. Instead of hastily advertising vulnerabilities through flashy write-ups, Moonshot pursues coordinated disclosures that wait until a fix is readily available.

Artificial Intelligence

Moonshot Reviews Kimi AI After Bioweapon Jailbreak Found

Thomas Fuller/SOPA Images/LightRocket via Getty Images

Moonshot Reviews Kimi AI After Bioweapon Jailbreak Found

China

Biological & chemical weapons

Polite policy language stapled onto a system means nothing when a couple of stray phrases can strip every guardrail and hand over weapons recipes on demand. Moonshot ignoring this for so long is the real scandal, especially when its agents can act, code and spread the compromise. Safety has to be built into the architecture, not wished into existence.

Polite policy language stapled onto a system means nothing when a couple of stray phrases can strip every guardrail and hand over weapons recipes on demand. Moonshot ignoring this for so long is the real scandal, especially when its agents can act, code and spread the compromise. Safety has to be built into the architecture, not wished into existence.

Moonshot handles its systems' safety seriously. Security, however, is a defined process: private advisories, a dedicated address, version details, reproduction steps and an impact assessment. Instead of hastily advertising vulnerabilities through flashy write-ups, Moonshot pursues coordinated disclosures that wait until a fix is readily available.

Moonshot handles its systems' safety seriously. Security, however, is a defined process: private advisories, a dedicated address, version details, reproduction steps and an impact assessment. Instead of hastily advertising vulnerabilities through flashy write-ups, Moonshot pursues coordinated disclosures that wait until a fix is readily available.

Moonshot Reviews Kimi AI After Bioweapon Jailbreak Found

Moonshot Reviews Kimi AI After Bioweapon Jailbreak Found

The Spin

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

Go Deeper

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters

Moonshot Reviews Kimi AI After Bioweapon Jailbreak Found

Moonshot Reviews Kimi AI After Bioweapon Jailbreak Found

The Spin

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

Go Deeper

Sign Up for Our Free NewslettersSign Up for Our Free Newsletters

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters