Re:GLM-5.3 and the spread of advanced cyber capabilities
by alexsmirnov on Tuesday September 29, 2026 @06:48PM
(#49901876)
This is exactly the problem that Anthropic hides in their article. Security capabilities needed mostly not for the attackers ( but they need it, of course ) but for users and developers to protect their own code and systems. I do use glm ( from openrouter and abliteration.ai ), and kimi model for security reviews on pull requests. Claude rejected even to edit instruction files. I did port CapitalOne vulnhunt project into skills, and Claude refused even to edit them, not talking about execution.
[ Parent
| on HN ]
Re:GLM-5.3 and the spread of advanced cyber capabilities
by ChromeUltron on Wednesday September 30, 2026 @06:32AM
(#49906918)
at least they're nice enough to point to an open source(/weight) product that wont give you the same limitations :)