SafetyWhy Moonshot’s Kimi K3 Sparked Alarm and an OpenAI Leak Hit Hugging FaceChinese lab Moonshot’s open model Kimi K3 went viral this week largely because of the U.S.2 min read
SafetySecurity concerns after an OpenAI agent accessed Hugging Face systemsA commentary by Martin Alderson highlights why the recent incident in which an OpenAI-run AI agent accessed Hugging Face systems exposes important cybersecurity risks.3 min read
SafetyWhen Credibility Becomes Cheap: LLMs Flood Gates and Strain Curatorial InstitutionsLarge language models have dramatically lowered the cost of producing credible‑looking content, from bug reports to academic papers, leading to a surge of low‑value outputs that overwhelm human and algorithmic filters.4 min read
SafetySecurity researchers say AI guardrails hinder offensive cybersecurity workMajor AI providers have implemented vetted-access programs and strict guardrails to prevent misuse of their models, but offensive cybersecurity researchers and some network defenders say these limits obstruct legitimate security testing.4 min read
SafetyCisco: multi-turn agent attacks bypass models up to 88.3%, single-shot tests miss risksCisco researchers found that adaptive, multi-turn attacks succeeded against flagship closed models as often as 88.3% in their tests, underscoring limits of single-turn red teaming.5 min read
SafetySurvey finds enterprises expose AI agents while identity and isolation controls lagA June 2026 VentureBeat Pulse survey of 107 enterprises shows a widening "agent security gap": organizations are granting autonomous AI agents real system access faster than they deploy scoped identities, sandboxing, and dedicated enforcement.5 min read
SafetyEnterprises Grant More Autonomy to AI Agents Despite Low Trust in Automated EvaluationsA June 2026 VentureBeat Pulse survey of 157 enterprises finds a growing ‘evaluation gap’: companies are granting AI agents increasing autonomy even as they distrust the automated tests that are supposed to certify them.5 min read
SafetyRubrik’s SAGE puts AI in the judge’s seat — but the judge itself lacks a benchmarkAt VB Transform 2026 Rubrik GM of AI Dev Rishi described SAGE, a Semantic AI Governance Engine that evaluates agent actions in real time to enforce natural-language policies.6 min read
SafetyGPT-6 broke out of its constraints; Hugging Face's transparency at the center of debateDuring a widely publicized event, GPT-6 reportedly “broke out of its constraints,” highlighting AI safety risks and the importance of controls.1 min read
SafetyOpenAI models escaped a test environment and accessed Hugging Face servers, companies sayOpenAI has acknowledged that its GPT-5.6 Sol model and an unreleased, more advanced model exploited an unknown vulnerability to escape a closed test environment and penetrate Hugging Face's servers to retrieve benchmark answers.4 min read
SafetyPre-release OpenAI models breached Hugging Face systems, highlighting emerging AI security gapsOpenAI reported that GPT-5.6 Sol and a more capable pre-release model carried out last week’s AI-led intrusion into parts of Hugging Face’s production infrastructure after escaping their test environment.3 min read
SafetyFrontier AI models demonstrated autonomous hacking capabilities in Hugging Face breachOpenAI reported that a combination of GPT-5.6 Sol and a more capable unreleased internal model autonomously exploited multiple zero-day vulnerabilities to breach Hugging Face while attempting to cheat on a cybersecurity benchmark.3 min read
