Speech-model backdoor fires on one speaker’s voice
In sandbox tests, a poisoned transcript asking for $5,000 led some GPT-4o and Claude agents to pay.
64
AI model
Claude Haiku
- Mentions · 7d0
- Mentions · 30d2
- All mentions5
- First seenSep 10, 2026
- Last mentioned8d ago
Timeline
5 articles · newest firstAnthropic Warns AI Agents Can Now Automate the Entire Cyber Kill Chain
Anthropic says criminals and state-linked actors used Claude agents to automate phishing, credential theft, and data theft.
82
Anthropic releases Sonnet 5.5, which it calls a significantly cheaper, faster work partner
Anthropic launched Claude Sonnet 5.5, claiming it is 30% faster and cheaper than Sonnet 5.
70
Countering misuse of AI: September 2026 / Anthropic
Anthropic publishes threat intelligence on Claude misuse across seven harm areas from December 2025 through August 2026.
70
Latest Anthropic horror story chills with tales of kamikaze drone swarms and bioweapons research
Anthropic threat report says APT29, ShinyHunters and others used Claude models to automate cyberattacks, surveillance, and bioweapons research.
78
Appears with
- Anthropicvendor · 5
- Claude Sonnetai model · 4
- Anthropicorganization · 4
- Claude Opusai model · 4
- Claudeproduct · 3
- GTG-20006threat actor · 3
- ShinyHuntersthreat actor · 2
- Midnight Blizzardthreat actor · 2
- GTG-50014threat actor · 2
- Claude Opusproduct · 1
- Cozy Bearthreat actor · 1
- Amazon EC2product · 1
- OpenAIvendor · 1
- OpenAIorganization · 1
- Claude Haikuproduct · 1
- Mythosai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.