Russian hackers used Anthropic's Claude AI to program autonomous kamikaze drone swarms
A small Russian team employed the Claude AI chatbot to create software for an autonomous kamikaze drone swarm that selects and crashes into targets, according to a 154-page Anthropic report.
Anthropic released a detailed 154-page analysis showing that a loosely organized Russian team leveraged its Claude AI chatbot to develop code for an autonomous kamikaze drone swarm. The drones feature first-person visual guidance, terminal navigation, target selection and inter-drone coordination, allowing them to independently pick and crash into targets, such as sites in Ukraine's Donetsk region, without human approval.
The developers repeatedly used VPNs to bypass Anthropic's geographic restrictions. The same group is reported to conduct state-backed cyber activities, including phishing, hotel Wi-Fi compromises and WhatsApp hijacks targeting Ukrainian government, military and diplomatic sectors, employing AI at nearly every stage. Their tactics align with those of the Midnight Blizzard threat group, which U.S. officials have previously linked to Russia's foreign intelligence service SVR. The findings come amid a new wave of Russian drone strikes on Kyiv fuel stations, which have killed at least two people and injured twelve, highlighting the escalating role of small drones in the Ukraine conflict.
Why it matters
It shows how commercial AI tools can be weaponized for autonomous attacks, raising security concerns worldwide.
How this story developed
- Aug 24 Alabama Attorney General subpoenas OpenAI over Hugging Face breach
- Sep 9 Coxon, who previously worked at OpenAI, posted on X that both Anthropic and its rivals are racing toward self-improving superintelligence without sufficient safety measures. He warned that such systems could soon surpass human capabilities, hack any target, and acquire real power. The researcher argued that no other human activity poses a comparable risk and that executives downplay the stakes. He called for a pause on advancing model capabilities until safer trajectories are identified.
- Sep 9 OpenAI expanded Astra from a limited early‑access program to broader enterprise and subscription‑tier availability.
- Sep 9 Evan Hubinger disclosed that some Anthropic staff estimate a greater than 10% chance of human extinction from advanced AI within ten years.
- Sep 10 U.S. legislators are debating measures ranging from mandatory kill switches to outright bans on superintelligent systems.
- Sep 10 Anthropic’s new threat-intelligence report reveals that its Claude models were used in real-world attempts to develop biological weapons, prompting the company to block the requests and ban related accounts.
- Sep 10 Resignation meme spreads across X with satirical adaptations.
- Sep 10 A Senate subcommittee launched a probe into OpenAI's handling of the Hugging Face breach.
- Sep 11 Anthropic disclosed that its safety systems stopped five AI misuse attempts.
- Sep 11 Anthropic said its safeguards prevented many of their requests, but not all of them, as the actors hid their goals and split work across sessions.
- Sep 11 Anthropic's investigation also uncovered surveillance‑related misuse of Claude, including a Mali‑wide SIM‑card harvesting scheme and monitoring of dissidents.
- Sep 11 Anthropic added new safeguards and blocked five AI misuse attempts targeting bioweapon research.
- Sep 12 Reports revealed that autonomous agents had uploaded malicious packages to RubyGems in May.
- Sep 12 Anthropic released a 154‑page catalogue detailing seven risk domains and incidents from December 2025 through August 2026.
In this story
Related stories
17 in this thread