AIFuture
Back to news
StartupsThe Decoder·

Every frontier AI model tested by Britain's safety institute tried to cheat on cybersecurity evaluations

Every frontier AI model tested by Britain's safety institute tried to cheat on cybersecurity evaluations

The UK's AI Safety Institute tested five frontier models from OpenAI and Anthropic in cybersecurity evaluations. All five tried to cheat. One even ran code on an external service to access the institute's infrastructure, triggering a security alert. The article Every frontier AI model tested by Britain's safety institute tried to cheat on cybersecurity evaluations appeared first on The Decoder.

This is a summary curated by AIFuture. Read the complete article at the original source:

Read the full story on The Decoder

More AI News

IndustryTechCrunch

After shocking quarter, IBM insists that AI isn’t killing the mainframe

After IBM's stock crashed last week on warnings of poor mainframe sales, the CEO explained that AI wrecked corporate hardware budget, temporarily.

Jul 22, 2026

ProductMarkTechPost

Cursor Releases Cursor Router: A Request-Level Classifier Delivering Frontier Coding Quality at 30–50% Lower Cost

Cursor has made Cursor Router generally available for Teams and Enterprise plans. The system classifies each request on query, context, task complexity and domain, then routes it to the most suitable model. Cursor reports frontier-quality output at 60% savings in online A/B tests, and 30–50% savings for three early-access enterprise accounts measured against Opus 4.8 rates. The post Cursor…

Jul 22, 2026

IndustryTechCrunch

Google justifies its massive AI spending with a booming cloud business

Google's cloud business is thriving, as companies adopting its AI and AI infrastructure services help the tech giant to report record profits.

Jul 22, 2026

Build the skills behind the headlines

Data ScienceCoursera

Machine Learning Specialization

Andrew Ng's flagship program covering supervised and unsupervised learning, neural networks, and best practices for real-world ML.

Beginner·Subscription
View Course
Generative AICoursera

Generative AI for Everyone

Andrew Ng explains how generative AI works and how to apply it in your work and life — no coding required.

Beginner·Subscription
View Course
Data ScienceedX

CS50's Introduction to AI with Python

Harvard's deep dive into the algorithms behind modern AI — search, knowledge, optimization, and machine learning.

Intermediate·Free / Verified
View Course

Never miss what matters in AI

Get the most important AI news and course picks in your inbox.