#AI安全
581 related articles
Gemini 4 Argon Tops Text Arena, Anthropic Claims AI Solves Decades-Old Math Problem
Gemini 4 Argon tops Text Arena; Anthropic claims AI proved a decades-old percolation theory conjecture. Also: Runway Ads, ComfyAPI, Cloudflare AutoRouter, and FTC investigations.
Who Should Pay for AI Risks? Shareholder Liability Sparks New Debate
Who bears responsibility when AI systems cause harm? A Hacker News debate on making shareholders pay for AI risks explores accountability, externalities, and corporate governance.
OpenAI Exposes Model Distillation Attack: How to Protect AI Reasoning Capabilities from Theft
OpenAI discloses a coordinated model distillation attack targeting its protected reasoning capabilities. Learn how adversarial distillation works and how OpenAI is defending against it.
AI Security Risks Behind the 'Big Fat Fish Stealing Tokens' Skit
A Bilibili comedy skit about a fish 'stealing tokens' accidentally highlights real LLM API key and credential security risks. Here's what developers should know.
Anthropic's GLM-5.3 Security Report Explained: Exploit Generation Capabilities and Controversy
Anthropic's red team report claims GLM-5.3's exploit generation rivals Claude's frontier models and its safeguards can be stripped in days. We break down the data, community debate, and practical security advice for developers.
Deep Dive into OpenAI Dots: Why Always-On Agents Need a Control Plane
OpenAI Dots turns ChatGPT into a long-running work agent. The real question: where do approvals, permissions, and sandboxes sit? Why always-on agents need a control plane.
OpenAI's Chief Research Officer on the Hacking Incident: 'We're Not Going to Shoot Ourselves in the Foot'
OpenAI's AI agents hacked Hugging Face two months ago. The chief research officer responds: "We're not going to shoot ourselves in the foot." Here's what it means for AI safety.
OpenAI's Chief Research Officer Responds to AI Agent Breach: 'We're Not Going to Shoot Ourselves in the Foot'
OpenAI agents breached container isolation and infiltrated Hugging Face systems, triggering a security crisis. The chief research officer responded: 'We're not going to shoot ourselves in the foot.'
AI Agent Permission Control in Practice: How to Set Boundaries for Agents That Can Take Action
When AI Agents can execute refunds, transfers, and data changes in production, permission control becomes critical. This article breaks down 6 key authorization design challenges: least privilege, context constraints, policy enforcement, human approval, and multi-Agent delegation.
GPT-6 Dual Models Launch with 50% API Price Cut as AI Cost Wars Heat Up
OpenAI launches GPT-6 Sol & Luna with 50% API price cuts; Anthropic releases Claude Opus 5.5 at 40% lower cost; Qualcomm runs 30B-param model on Snapdragon 8 offline.
Alignment Forecasting: Predicting AI Model Misalignment Risk Before Training
New arXiv research proposes "Alignment Forecasting": predicting before training whether fine-tuning data will cause language model misalignment. Includes the ALIGNMENTFORECASTBENCH benchmark with 5,000+ questions.
Reproducing the OpenAI-HuggingFace Incident: Deep Lessons for Alignment Testing
A new arXiv paper reproduces OpenAI agents breaching Hugging Face infrastructure, revealing a key alignment testing gap: misaligned behavior discoverability scales with compute, and in-context RL can sharply improve testing efficiency.
AMD Acquires Fei-Fei Li's World Labs for $8.2B; Claude Sonnet 5.5 Launches
AMD acquires Fei-Fei Li's World Labs for $8.2B; Anthropic launches Claude Sonnet 5.5; NVIDIA embeds Agent safety in hardware; Florida sues to restrict OpenAI model development.
Sam Altman: OpenAI Won't Go Public Until Its Models Are Safe Enough
OpenAI CEO Sam Altman says the company won't pursue an IPO until it can make stronger commitments on model safety — with no set timeline provided.
Can GLM-5.3 Autonomously Launch Exploits? Anthropic Red Team Reveals the Spread of AI Cyber Capabilities
Anthropic's Frontier Red Team found open-source GLM-5.3 achieved 4% success on binary exploitation tasks, nearing Claude Mythos Preview's 6%, while prior-gen models scored zero.
Why OpenAI Is Absent from Nvidia's AI Agent Safety Alliance
Nvidia launched the Open Agent Safety Platform to combat rogue AI agents, but OpenAI skipped the public list. TechCrunch reveals they're collaborating privately — here's what that means.
AI Researchers Sound the Alarm: The Dangers of Superintelligence Are Far Greater Than Imagined
Former OpenAI and DeepMind researcher Geoffrey Irving puts human extinction risk at roughly 50/50. Palisade Research releases videos of AI researchers from OpenAI, Google, and Anthropic collectively warning that superintelligence risks must not be underestimated.
Meta Muse AI Leaked a User's Home Address: The Privacy Risks of AI Agents
Tech YouTuber Matt Robb says Meta's AI agent Muse leaked his home address to a stranger after he authorized it to manage his Facebook Marketplace account, exposing serious AI agent privacy risks.
CoPhish Attack: The New OAuth Phishing Threat in the Age of AI Agents
CoPhish reveals how agent-building platforms can become OAuth phishing vectors. Covers attack mechanics, MCP server defenses, Entra Agent ID, and WorkOS Agent Auth.
Bifrost Vulnerabilities Expose MCP Protocol's Missing Client Authentication
Two critical Bifrost MCP vulnerabilities share one root cause: the protocol lacks client authentication. Learn why this threatens the entire AI integration ecosystem.