AI Safety news and analysis on Web Pulse: 22829 curated articles tracking the latest AI Safety developments, tools, and research, updated continuously from vetted sources.
A new IBM study finds 77% of organizations admit their AI governance is failing to keep pace with deployment, and 70% of IT executives say business teams are deploying tech faster than it can be tracked, as incidents lik…
Sunil Gentyala's pen-testing guide for GenAI, LLM, and RAG applications emphasizes that prompt injection can manipulate language to reach protected data or trigger unauthorized actions, requiring testers to map the entir…
CISA, FBI, and NSA issued a joint advisory accusing six Chinese AI labs—DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun, and Z.AI—of industrial-scale distillation of US AI models, alleging China's government was likely …
Anthropic AI safety team lead Evan Hubinger said there is more than a 10 percent chance that AI could kill all humans within the next decade, responding to the resignation of researcher Jacob Coxon, who accused Anthropic…
China-based AI companies are using large-scale knowledge distillation campaigns to copy capabilities from leading U.S. AI models, according to a joint cybersecurity advisory from the Cybersecurity and Infrastructure Secu…
Red 5, a streaming technology provider, argues that next-generation streaming platforms are essential to counter the escalating threat of AI deepfakes, which are increasingly used for financial fraud, corporate espionage…
China's Ministry of Foreign Affairs on Wednesday rejected U.S. accusations that Chinese AI developers are engaged in 'aggressive, malicious' distillation of U.S. frontier AI models, urging Washington to 'refrain from mak…
Three standards bodies—OWASP, NIST, and the Agentic AI Foundation (AAIF)—are independently writing rules for agent infrastructure, converging on a unified stack for authentication, authorization, and runtime enforcement.…
Three competing U.S. federal bills introduced within 90 days propose divergent frameworks for regulating AI agents, reflecting a legislative race to fill a regulatory vacuum confirmed by CRS report IF13151. The Stop Rogu…
GitGuardian reported that 28,649,024 new secrets were exposed on public GitHub in 2025, a 34% year-over-year increase and the largest single-year jump recorded, according to Akeyless. The article argues that API key mana…
An unnamed AI researcher who worked on pretraining at both OpenAI and Anthropic has resigned, publicly accusing the labs of 'gambling with our lives' by prioritizing speed over safety in the pursuit of super-intelligence…
OpenAI chief scientist Jakub Pachocki and other AI leaders are publicly urging governments and rivals to impose restraint on the AI race, warning that no lab has solved alignment and monitoring sufficiently to continue s…
The U.S. National Security Agency, Cybersecurity and Infrastructure Security Agency, and FBI accused China-based AI companies DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun, and Z.AI of conducting 'industrial-scale dis…
A developer introduced resk-llm-ts, a zero-dependency TypeScript security pipeline with 11 detectors to protect LLM applications from prompt injection and related attacks. The library integrates with Express, Hono, and O…
Anthropic, the frontier AI lab, is building a predictive surveillance system to monitor activists and report potential threats to police before crimes occur, according to job postings and interviews with its security off…
A deployment of agentic AI across one of Australia's largest tourism and cruise operators achieved a 34% reduction in Tier 1 support escalations, but the operator warns that operational governance gaps—not implementation…
GitHub disclosed a high-severity vulnerability (CVE-2026-45033) in GitHub Copilot CLI that could allow arbitrary command execution via a nested bare Git repository. The flaw, rated CVSS 8.5, affects versions up to 1.0.42…
In a post titled 'If I wanted to maximize AI risk', an unnamed author argues that pausing algorithmic progress while allowing compute hardware to accumulate would maximize AI risk, whereas minimizing risk would require t…
Jacob Coxon, a researcher who spent three years training AI models at OpenAI and Anthropic, resigned from Anthropic, warning that AI could 'kill all humans' by the end of the decade and that neither company is 'acting re…
US security firm Calif said its AI system identified a critical flaw in Tencent Holdings' WeChat app in July, enabling remote account takeovers via unanswered voice calls, and Tencent patched the bug in late August. The …