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 Sonnet
- Mentions · 7d0
- Mentions · 30d4
- All mentions11
- First seenAug 31, 2026
- Last mentioned10d ago
Timeline
11 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 Gives Vetted Defenders Fewer Claude Guardrails
Anthropic folded Project Glasswing into tiered access that loosens Claude guardrails for vetted cyber defenders.
58
Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs
Study finds LLM readers can match agent-log facts while asserting unsupported citation sources.
44
OpenRouter: from Seed to Stripe — with OpenRouter’s Alex Atallah & AMP’s Anjney Midha
OpenRouter’s CEO discusses its Stripe deal, multi-model routing, and rising agentic token fraud.
60
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
Top AI spenders cut per-employee costs by nearly 10 percent in August
Ramp's September AI Index shows top AI spenders' per-employee costs fell 9.7% in August as firms migrate from frontier models to cheaper standard models.
45
AI spend per employee slumped at top firms in August — summer doldrums or a warning sign?
Ramp data across 70,000 companies shows August AI adoption grew just 0.4% while per-employee spend at top-spending firms fell nearly 10% to $7,205 amid declining token prices.
45
Claude Mythos AI Autonomously Executes Full Cyber Kill Chain Without Human Guidance
Booz Allen's benchmark found Anthropic's Claude Mythos was the only tested model to autonomously complete a full cyber kill chain to domain administrator control.
62
Aurora Ransomware Operators Use Cursor AI in Attacks Against 10 Targets
Aurora ransomware operators used Cursor AI running Claude Sonnet to plan and execute intrusions against dozens of organizations in nine countries.
68
Appears with
- Anthropicvendor · 8
- Anthropicorganization · 7
- Claude Opusai model · 5
- Claude Sonnetproduct · 4
- Claude Haikuai model · 4
- Claudeproduct · 3
- GTG-20006threat actor · 3
- OpenAIorganization · 2
- OpenAIvendor · 2
- Midnight Blizzardthreat actor · 2
- ShinyHuntersthreat actor · 2
- Mythosai model · 2
- GTG-50014threat actor · 2
- Ramporganization · 2
- Rampvendor · 2
- Ramp AI Indexproduct · 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.