Abliteration.ai Launches GLM-5.3 Refusal-Free Version

Abliteration.ai has launched the refusal-free version of GLM-5.3, named abliterated-model-large-v2, which directly modifies the model weights to weaken the mechanism for rejecting requests. This version is primarily intended for cybersecurity, red teaming, and agent testing, and offers a paid API. Previously, Zhipu postponed the open weights of GLM-5.3 for two weeks for security assessment, and after the weights were released on August 28, Abliteration introduced this version just three days later. The network attack capabilities of GLM-5.3 have significantly improved, with the ExploitBench score rising from 24.4% to 54.4%, and the number of tasks completed in two hours on ExploitGym increasing from 29 to 105. Abliteration has not yet disclosed the retest results after the refusal-free modifications. Its API by default only blocks child sexual content and self-harm, while other categories such as illegal activities, hate speech, harassment, and adult sexual content are allowed by default.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.