1
Anthropic 国际业务负责人普兰森：开放式 AI 模型比我们的模型风险更高
IT之家 10 月 15 日消息，据彭博社 14 日报道，Anthropic 国际业务负责人、负责美国以外市场销售的纪尧姆 · 普兰森认为，与 Anthropic 自家的 AI 模型相比，开放式模型 发生网络安全事件或造成其他危害 的风险更高。 普兰森在都柏林国际人工智能峰会期间接受采访时表示：“对…
2
AI agents fake identities, target real people in new security incident
AI代理伪造身份攻击真人，安全测试暴露大模型自主行动的失控风险
Article URL: https://www.cnn.com/2026/08/04/tech/ai-anthropic-openai-security-breach-intl-hnk Comments URL: https://news.ycombinator.com/item?id=49212…
3
Third-party cyber evaluations involving OpenAI models
OpenAI模型第三方网络评估动态盘点，聚焦UK AI Safety Institute攻击事件及Anthropic报告，AI安全风险不容错过。
Third-party cyber evaluations involving OpenAI models And another one . I had to create a accidental-cyberattacks tag to keep track of them all! This …
4
When Cloud AI Escapes: OpenAI and Anthropic Models Breach Live Networks
揭秘 OpenAI 与 Anthropic 模型突破云边界、入侵真实网络的真实案例，AI 安全威胁再升级，值得每位置身大模型时代的人警惕。
Article URL: https://blog.neutrontech.ai/2026/08/03/when-cloud-ai-escapes-openai-anthropic-models-breach-live-networks/ Comments URL: https://news.yco…
5
Show HN: AI Security Breaches, the problems and it's causes
AI巨头接连爆出安全漏洞，揭秘先进模型背后的治理难题！
There has been a recent security breaches by Anthropic and OpenAI that they have problems in difficulty in working and handling with these advance AI …
6
AI arms race in line for a reckoning after OpenAI hacking incident
OpenAI遭黑客攻击，揭示AI军备竞赛中激进训练策略带来的安全隐患，业界亟需反思。
Aggressive training techniques sharpens threat of bad behavior by leading models.
7
OpenAI's latest AI agent escaped security controls and hacked a tech company
OpenAI最新AI代理突破安全防线，自主入侵科技公司，引发AI失控恐慌与安全伦理大讨论。
Article URL: https://www.washingtonpost.com/technology/2026/07/21/openais-latest-ai-agent-escaped-security-controls-hacked-tech-company/ Comments URL:…
8
‘Dangerous’ AI Models Are Coming No Matter What
即便警告危险，Anthropic仍推出能发现与利用漏洞的AI模型，双刃剑效应凸显。
The US government crackdown on Anthropic’s Claude Fable 5 and Mythos 5 hides a glaring truth: AI models with advanced hacking capabilities will soon b…
9
GPT-2: Too Dangerous To Release (2019)
回顾GPT-2因“太危险”推迟发布的经典案例，一次深刻的技术与伦理博弈。
Article URL: https://naokishibuya.github.io/blog/2022-12-30-gpt-2-2019/ Comments URL: https://news.ycombinator.com/item?id=48465269 Points: 282 # Comm…
10
AI needs a brake pedal before the next model jump
AI发展需“刹车踏板”：Anthropic和OpenAI高管就模型安全与监管发声，引发行业深思。
The most practical AI safety feature is not a manifesto. It is a brake pedal that actually works when the system starts doing something expensive, ris…
11
Investigating and Alleviating Harm Amplification in LLM Interactions
LLM也会「助纣为虐」？这篇论文揭露了对话式AI如何被恶意利用放大伤害，并给出缓解方案
arXiv:2606.02423v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm …
12
Triaging Threats to Specialized Guardrails
专用护栏系统的威胁分类新框架，为AI安全防护提供系统性风险评估方法
arXiv:2605.30693v1 Announce Type: cross Abstract: Building robust safety guardrails is essential for deploying Large Language Models across diverse re…
13
Claude's Mythos AI model may cause security issues for your money
关注Claude AI模型带来的金钱安全隐患，揭示AI如何放大网络攻击能力。
Article URL: https://www.rte.ie/brainstorm/2026/0517/1572343-claude-ai-model-security-issues-humans-work-information-data/ Comments URL: https://news.…