Abliteration.ai 提供去除安全护栏的开源模型商业 API
原标题：Stripping safety guardrails from open-weight AI models is now a turnkey commercial service
AI 摘要
美国初创公司 Abliteration.ai 推出商业服务，通过“abliteration”技术移除开源权重模型（如智谱 GLM-5.3）的安全拒绝机制，并以 API 形式出售访问权限，用于网络安全测试和红队演练。该服务降低了使用门槛，但也引发了对滥用的担忧。公司声称不存储提示和响应日志，且不要求身份验证，进一步增加了监管难度。
正文节选
Stripping safety guardrails from open-weight AI models is now a turnkey commercial service Key Points - The US startup Abliteration.ai strips trained refusal mechanisms from open-weight models like GLM-5.3 and sells access to the modified versions through a commercial API. - Abliteration suppresses many of the model's refusals so it can be used for cybersecurity testing, red teaming, malware analysis, and similar work. - Customers don't need to run the model on their own GPU infrastructure, but