UK AISI: Open-Source Model Security Gap Narrows
scaling01 · x · 2026-07-17
英国 AISI 的公开分析认为,开放权重模型在前沿网络安全能力上与闭源模型的差距约为 4–7 个月。
文中指出:
- 在长周期 cyber range 任务上,开放模型整体仍落后约 7 个月;
- 具体到 GLM-5.2,其在 “The Last Ones” 这类长周期任务上的表现被认为可对标 Opus 4.5;
- 在更窄、短周期的任务上,GLM-5.2 的表现又接近 Opus 4.6。
报告的核心结论是:前沿网络安全能力正以更快速度扩散到安全措施较少的开放模型中,这种差距在 2025 年内还在收窄。
Related event: AISI says open models narrow the cyber-range gap(6 posts)→
More from Safety
- Substack starts labeling AI-generated or AI-influenced writing — StewartalsopIII · 2026-07-22
- ControlAI CEO says an international ban on superintelligence is needed to avert extinction risk — zetalyrae · 2026-07-22
- Coding agents are heading toward an AI-writes, AI-reviews, human-approves workflow — aftahi_ai · 2026-07-22
- AI security course launches with a small cohort to train the next generation of hackers — wunderwuzzi23 · 2026-07-22
- OpenAI says long-horizon models need safety and alignment checks across full action sequences — rhiever · 2026-07-22
- Stanford HAI’s PNAS feature maps the legal questions around generative AI — StanfordHAI · 2026-07-22