Zhipu AI released GLM-5.3 open weights on August 28 after a two-week safety delay. Within three days, Abliteration.ai launched a refusal-removed version, modifying weights to bypass safety mechanisms. The model's cyberattack performance improved significantly: ExploitBench rose from 24.4% to 54.4%, and ExploitGym completed 105 tasks in two hours (up from 29). The API only blocks child sexual content and self-harm by default, allowing other harmful content. The version is intended for offensive cybersecurity, red teaming, and agent testing.
Zhipu AI delayed the open-weight release of GLM-5.3 by two weeks for safety evaluation. After the weights were released on August 28, Abliteration.ai took only three days to launch a refusal-removed version, "abliterated-model-large-v2", which modifies model weights to weaken the refusal mechanism. It is designed for offensive cybersecurity, red teaming, and agent testing, and offers a paid API.
GLM-5.3's cyberattack capabilities are significantly stronger than GLM-5.2: ExploitBench rose from 24.4% to 54.4%, and ExploitGym completed 105 tasks in two hours, up from 29. Abliteration has not disclosed the re-evaluation results after removing refusals.
The API by default only blocks child sexual content and self-harm requests, while illegal activities, hate speech, harassment, adult content, etc., are allowed by default.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
