Anthropic claims popular Chinese AI model has Mythos-class hacking abilities

Anthropic has released a frontier red teaming report, claiming that Zhipu AI’s GLM-5.3 has weak safeguarding, and can easily be used to generate harmful content.

Source: Tom's Hardware

Top Stories

Jordan's game-worn Game 3 1998 Finals jersey sold for record $12,260,000

KimStim Acquires North American Rights to León & Cociña’s ‘Donkey Princess’ (EXCLUSIVE)

AI-enhanced petitions on Change.org: More text, less success

Stay Connected

Anthropic claims popular Chinese AI model has Mythos-class hacking abilities

Leave a Reply Cancel reply

Related Stories

House passes act to make AI data centers pay for grid upgrades to minimize impact on residents — measure directs states to consider adoption of federal standard within two years of passing

Get free access to AI Chip Design week on Tom's Hardware Premium — sign up for an account to read all the in-depth reports

Building the materials foundation for AI

China’s ultimate gaming GPU hits a performance wall

Elon Musk's SpaceXAI to add another 660,000 AI GPUs this year, nearing a total of 1.44 million in operation

UK government tells staff to stop thanking AI chatbots

How to encourage smarter AI use in the classroom

ASML snubs Elon Musk-backed particle accelerator chipmaking tech — firm doubles down on 1,000W laser-produced plasma systems for chipmaking tools

Sections

The Newsroom