How some AI models are more vulnerable to manipulation

The revelation last month that Claude was used "in ways that could support biological weapons development" was made possible, in part, because Anthropic's AI models operate on a closed system overseen by the company.Anthropic said it banned and reported accounts engaging in misuse of its AI and used the findings to strengthen safeguards.But that kind of oversight is more difficult with "open-weight" models. Unlike Claude, which is a closed-weight model, open-weight models can be run on a user's own hardware rather than on a company's cloud, making insight into how they're being used more challenging. They are also more vulnerable to jailbreaking and "model abliteration" — where the safety constraints of a model can be removed.Open-weight models tend to be cheaper than closed ones and can make powerful AI technology more accessible and customizable.China has embraced open-weight models, a development that researchers say is closing the AI capability gap between the country and the U.S.China-based AI company Moonshot says its most powerful open-weight model, Kimi K3, still trails behind the top models from Anthropic and OpenAI, but that it demonstrated "frontier-level performance" in some categories, "consistently outperforming" some frontier closed models.

For example, Kimi K3 performed better than advanced proprietary models like Claude Fable 5 and GPT-5.6 Sol in rebuilding software projects from scratch, according to Moonshot.What are open-weight models?An