中文翻译

摘要: AI in practice

Copy the url to clipboard

Share this article

Go to comment section

New Claude Mythos becomes the first AI model to clear all cyberattack simulations from Britain's AI safety agency

...

正文

AI in practice

Copy the url to clipboard

Share this article

Go to comment section

New Claude Mythos becomes the first AI model to clear all cyberattack simulations from Britain's AI safety agency

Matthias Bastian

View the LinkedIn Profile of Matthias Bastian

May 14, 2026

GPT-Image-2 prompted by THE DECODER

Key Points

The British AI Safety Institute (AISI) has revised its forecast for AI cyber capabilities, now estimating a doubling time of 4.7 months instead of the previous 8 months.

Models like Anthropic's Claude Mythos Preview and OpenAI's GPT-5.5 have already surpassed even this accelerated timeline.

In AISI simulations, a new Claude Mythos Preview checkpoint pulled off a 32-stage attack on a simulated corporate network in six out of ten attempts. It was also the first model to crack an industrial control system simulation, succeeding in three out of ten cases.

Ask about this article…

Frontier AI models are gaining cyber capabilities faster than anyone expected. The UK's AI Security Institute (AISI) has revised its estimates upward twice in just a few months.

In November 2025, the agency estimated that cyber capabilities were doubling every eight months. By February 2026, it had revised that figure to 4.7 months. Anthropic's Claude Mythos Preview and

OpenAI's GPT-5.5

have now "substantially exceeded" even that accelerated timeline, according to AISI. Whether this represents a new trend or a one-time jump remains unclear.

AI cyber capabilities are growing far faster than predicted. The latest models (Mythos Preview, GPT-5.5) have saturated AISI's test environment and deviate sharply from prior trends. The performance leap is so large that reliable forecasting becomes uncertain. | Image: AISI

Mythos Preview is the first model to clear both AISI cyber ranges

The biggest gains showed up in AISI's cyber ranges, complex attack simulations designed to test real-world hacking ability. One range simulates a 32-step attack on a corporate network

来源: Brave/the-decoder.com

采集时间: 2026-05-14 20:16:26