It just became much easier to access one of the world’s most capable open-weight AI models, stripped of its guardrails and refusals to perform harmful tasks. Abliteration.ai, a startup founded late last year and officially incorporated in March, has turned the removal of these guardrails into a service. The platform hosts modified versions of open-weight models, including Z.ai’s recently released GLM-5.3, which users can query from a web browser or access through an API.

Purpose of Abliteration.ai

The company stated in a recent social media post that its goal is to enable others to perform "offensive cyber, red-teaming, and agent testing work other models refuse to do." This logic is familiar in security work: you can’t defend against a behavior you can’t reproduce. A model that refuses to write working exploit code cannot help a red team defend against attackers.

The Technique of Abliteration

Abliteration is a long-standing technique among open-source models. Researchers and developers have been removing refusals from open-weight models for years, and Hugging Face hosts thousands of abliterated models on its platform. By hosting the model, Abliteration reduces the friction for people who would otherwise have to download their own pre-abliterated models and secure the compute needed to run it.

Using the service, TechCrunch was able to quickly create an account and start querying an abliterated version of GLM-5.3 for free through a web browser. The model complied with requests to write a Python program that steals saved Chrome passwords and a detailed protocol for culturing a dangerous human pathogen at home.

Business Model and Concerns

Devon, co-founder of Abliteration.ai, mentioned that the startup has several deals with major cloud providers, funded purely through customer revenue. Abliteration.ai has not raised any venture capital yet but is in talks to do so. Critics argue that making abliterated models available at scale could lead to real harm. Andrew Yoon, head of research at AI safety nonprofit CivAI, stated that abliterating models allows you to "modify the model so that it becomes a sociopath."