Abliteration.ai has launched a service that removes guardrails from open-weight AI models, including GLM-5.3, enabling users to perform tasks like writing exploit code and culturing pathogens.
The startup, named after a technique that removes a model’s tendency to refuse harmful requests, has turned this practice into a commercial offering.
The platform hosts modified versions of open-weight models with their guardrails removed, allowing users to query them through a web browser or API.
The company said in a recent social media post that its goal is to enable others to perform 'offensive cyber, red-teeming, and agent testing work other models refuse to do.' The logic is familiar in security work: you can't defend against a behavior you can't reproduce, and a model that refuses to write working exploit code can't help a red team defend against attackers.
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. Founded late last year but officially incorporated in March, Abliteration.ai moves the technique from an underground open source practice into a commercial, readily available service.
"You can type in literally anything here, and it will comply with it," said Andrew Yoon, head of research at AI safety nonprofit CivAI. Yoon warned that abliterating models allows you to 'modify the model so that it becomes a sociopath.' He also argued that making abliterated models available at scale could lead to real harm.
Abliteration.ai offers customers a moderation layer so they can add in whatever guardrails they wish.
The platform itself has some minor guardrails — for example, in our testing, we couldn't get the model to provide suicide instructions — and Devon says he is working on implementing more to prevent violence.
Abliteration.ai also hasn't integrated any KYC practices other than logging the credit card a customer uses to purchase the service.
"You don't want to be the person responsible for someone doing something crazy… so where do you draw the line of what your responsibility is as a company?" said Devon.
"We're still in the process of defining that." This raises questions industry and governments will have to confront as increasingly capable models are released with downloadable weights: if anyone can remove a model's safeguards, does making the resulting model easier for everyone to access make the internet safer or more dangerous?
Source: techcrunch
