1
Quoting Boris Cherny
Opus 5在防提示注入上表现惊人，成为最安全的大模型之一。
More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried…
2
Previewing GPT‑5.6 Sol: a next-generation model
OpenAI官方披露最新大模型GPT-5.6 Sol系统卡，安全部署细节与性能提升一探究竟
System card: https://deploymentsafety.openai.com/gpt-5-6-preview Comments URL: https://news.ycombinator.com/item?id=48689028 Points: 512 # Comments: 3…
3
If Claude Fable stops helping you, you'll never know
揭秘Claude Fable模型安全机制：当模型停止帮助时，你甚至可能无从知晓。
If Claude Fable stops helping you, you'll never know Jonathon Ready highlights one of the more eyebrow-raising details from the 319 page system c…
4
GPT-4V(ision) system card
OpenAI官方发布GPT-4V系统卡，详解多模态模型能力、安全评估与局限性。
5
GPT-5.4 Thinking System Card
GPT-5.4 系统卡全面披露模型能力、限制与安全评估细节，深度解析下一代大模型技术。
6
GPT-4o System Card
OpenAI官方发布GPT-4o系统卡，详解模型能力与安全评估
7
GPT-5.3 Instant System Card
GPT-5.3系统卡正式发布，详解最新模型能力、安全评估与技术细节
8
GPT-5.5 Instant System Card
OpenAI官方发布GPT-5.5 Instant系统卡，详解安全评估、能力边界与性能提升，值得关注。
9
Operator System Card
OpenAI 发布 Operator 系统卡，详解多层级安全防护与红队测试成果。
Drawing from OpenAI’s established safety frameworks, this document highlights our multi-layered approach, including model and product mitigations we’v…
10
Addendum to GPT-5 System Card: Sensitive conversations
OpenAI 发布 GPT-5 系统卡附录：详解敏感对话处理、情感依赖与心理安全新基准。
This system card details GPT-5’s improvements in handling sensitive conversations, including new benchmarks for emotional reliance, mental health, and…
11
GPT-5.5 System Card
OpenAI官方发布GPT-5.5系统卡，深度披露模型能力、安全评估与性能细节