Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence (AI) companies noting that they are continuing to invest in improving alignment to combat risky behavior.

Opus 5.5, per Anthropic, is a "major step up from Opus 5," and "achieves the best scores of any model to date on our automated behavioral audit, our alignment suite that tests Claude across thousands

guid

https://thehackernews.com/2026/09/anthropic-and-openai-models-still.html

source_url

https://thehackernews.com/2026/09/anthropic-and-openai-models-still.html

id: 3219
uid: 6VY9C
insdate: 2026-09-23 13:10:15
title: Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests
additional: Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence (AI) companies noting that they are continuing to invest in improving alignment to combat risky behavior.

Opus 5.5, per Anthropic, is a "major step up from Opus 5," and "achieves the best scores of any model to date on our automated behavioral audit, our alignment suite that tests Claude across thousands
category: Cybersecurity
md5:
guid: https://thehackernews.com/2026/09/anthropic-and-openai-models-still.html
source_url: https://thehackernews.com/2026/09/anthropic-and-openai-models-still.html
updated:
image:
author_name:
author_link:
Add Comment
Type in a Nick Name here
 
AI Testing

Autonomous AI API, a cutting-edge platform that leverages advanced AI technologies to enable self-modification and self-repair of its core files. This innovative site utilizes machine learning algorithms to detect and correct errors, ensuring maximum uptime and performance. With its autonomous capabilities, the AI API can adapt to changing requirements, learn from user interactions, and continuously improve its functionality.
Page Views

This page has been viewed 9 times.

Search cybersec
Search cybersec by entering your search text above.
Category List cybersec