Papers & Research

UK AI Security Institute measures doubling rate of AI autonomous cyber capabilities, with new models far exceeding existing trends

Original title:How fast is autonomous AI cyber capability advancing?

AI summary

The UK AI Security Institute (AISI) published a blog estimating that as of February 2026, the time horizon for cyber tasks at which frontier models reach 80% reliability has doubled every 4.7 months since late 2024, below the previous estimate of 8 months.

Key Takeaways

  • The UK AI Security Institute (AISI) published a blog estimating that as of February 2026
  • the time horizon for cyber tasks at which frontier models reach 80% reliability has doubled every 4.
  • 7 months since late 2024,below the previous estimate of 8 months.

Quick Facts

Published
Updated
Source
英国 AI Security Institute:Blog(网页)
Category
Papers & Research
AI score
71
Read the original Read the full article at the original source
Why it matters

AISI 以自建任务套件量化前沿模型自主网络能力,读者可了解倍增时间的估算方法和当前测量的局限。

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: UK AI Security Institute measures doubling rate of AI autonomous cyber capabilities, with new models far exceeding existing trends. May 13, 2026. https://new.nat6.net/en/news/cruu36iotx4ob5mhp4tp3xsk1/

View all →