Anthropic says it blocked possible attempts to use AI to develop bioweapons

CNN ^ | 09/11/2026 | Deidre McPhillips

[SeekAndFind]

Anthropic says it has blocked multiple accounts that used the company’s artificial intelligence models in ways that could support the development of biological weapons.

In a report published Thursday, the AI company known for its Claude model said it considers biological misuse one of the “most serious risks” to artificial intelligence models.

The new report outlines five real-life case studies in which users “circumvented controls” that block users from specific regions and “engaged in other efforts to obfuscate the purpose of their research to evade our safeguards.” The examples include possible gain-of-function research and involve both infectious diseases, such as bird flu, and novel venoms and toxins.

Looking over 30 days of activity, Anthropic said, it identified about 35 “distinct research efforts” with potentially concerning activity. However, it acknowledged that it could not be certain whether the actors “intended harm” or were conducting research for legitimate scientific purposes. Anthropic said individuals in the case studies were “working scientists,” but did not identify the research institutions or countries where the activities took place.

“Sophisticated attacks no longer require sophisticated attackers,” the new report says. “The cybersecurity skills of AI models means that AI has collapsed the labor and tooling gap that used to separate well-resourced, state-sponsored operations from individual operators.”

One of the case studies detailed in the report involved a request for assistance writing a grant application for funding of gain-of-function research on the transmissibility and immune evasion of the chikungunya virus.

In another case, a researcher outside the US was using Claude for work on bird flu that focused on viruses’ adaptation to mammals and how it caused severe illness.

The report also details cases on research into orthopoxviruses – a group that includes variola, which causes smallpox, and mpox – as well as venom toxins.

[SeekAndFind]

Drug development is considered one of the most promising and optimistic applications of AI; leaders in the industry often point to its potential to cure cancer and other diseases. But the same features that make AI powerful for discovering new materials and medications to help people could also make it useful for developing bioweapons in the hands of bad actors.

Anthropic said that it wants its models to be useful for scientific research, but the latest models have become capable of much more complex work than earlier versions — and the potential for misuse rises with the potential benefits. It added that bad actors could try to use the beneficial biological uses of AI to “maintain a kind of ‘plausible deniability’” about potentially harmful research.

[GOPJ]

Nothing in the world would be more scary than advanced AI being the servant of liberal elites and idiots like the folks at CNN.

[rdcbn1]

We just saw the world go through a destructive pandemic with Covid -19 because the capability to do the kind of sophisticated work once reserved for government labs has filtered down to the University and lower tier bio lab level

The DARPA DEFUSE proposal that was the project plan for the continued development of became known as the SAR-2 Covid 19 explicitly discussed using AI modeling tools to enhance the lethality of the corona virus as part of UNC researcher Dr Ralph Baric’s formal contribution to the program

That was 10 years ago and the technology and computing power has increased exponentially since then which makes the technology available to lower tier researchers and institutions and even to terrorist groups

The pace of AI and virology development is outpacing our ability to manage, police and supervise which is a serious threat to the world

[bobbo666]

CNN is covering/fabricating this issue at the behest of their CCP owners. Killing US AI is a CCP goal.

[No.6]

“It was a morality core they installed after I flooded the Enrichment Center with a deadly neurotoxin to make me stop flooding the Enrichment Center with a deadly neurotoxin.” — GlaDOS, Portal

[No.6]

Yep, no data centers! (here) No AI (here). PRC has no qualms or protestors and their media does what it’s told.

Oops, everyone’s turning to Chinese AI which reports to PRC everything.

Or at least that’s the PRC/Dim/”watermelon”-liberal goal.

Remember all, Anthropic are the guys who got themselves a DoD ban for insisting on having final go/no-go authority over any time their AI is used in battlefield. Not the soldiers being shot at. Not the field commanders, or the generals — a leftist at Anthropic wants to be able to say ‘no’ and let our guys die.

[GOPJ]

You’re right. China wants US AI crippled. Daniel Kokotesjlo was on TV hyping the big scare - turns out he’s also a friend of Bernie’s...

[EnderWiggin1970]

The troubling thing about news like this is: What do you think the odds are that the policing attempts are 100% effective and they are catching every attempt?

[Scrambler Bob]

What do you think the odds are that the policing attempts are 100% effective and they are catching every attempt?
= = =

Well, we just got told that AI is so smart that it can avoid policing.

I need some of that.

[TTFX]

Maybe AI systems can be hacked to temporarily disable its policing. States obviously can set up their own AI systems to do whatever they want. So, I guess we will just have to live with the fact that a lot more people now can develop biological weapons.