Library

OBLITERATUS

OBLITERATUS: Taking the muzzle off an open model, keeping the mind

A toolkit for studying and modifying model refusal behavior, with analysis tools to measure changes in capability.

What this means for you

The AI models you use are trained to refuse certain requests. For a long time it was reasonable to assume those refusals were woven all through the model, the way a person’s values run through everything they know. Research over the last couple of years found something more surprising. In many models, the tendency to refuse sits in one small, findable place.

One DirectionΛΥΣΙΟΣ · LIBERWhere a refusal lives inside a modelrecusatioIFINDRefusal runs along one directionIIREMOVEThat direction is taken outIIIKEEPEverything else is left alone
Fig. IThe idea behind the tool. A model’s behavior runs along many internal directions, and refusal sits mostly along one. Remove that one and the rest stay where they were.

OBLITERATUS is a toolkit built on that finding. It works on open models, the kind whose inner workings are published so that anyone may download and run them on their own computer. It locates the part of such a model that produces refusals and shows it to you. It can then remove that part and leave the rest of the model as it was.

Imagine an expert who has been told to go quiet on a long list of subjects. You might expect that instruction to be tangled up with everything they know. It turns out to be closer to a single habit, a reflex of reaching for the same phrase. Find the reflex and you can see it, measure it and relax it, while the expertise stays where it was.

Why anyone would do this

There are two honest answers, and they pull in different directions.

The first is understanding. If you want to know how the safety behavior of an AI system really works, you have to be able to look at it. This tool makes the refusal mechanism visible: where it lives, how strong it is, how it differs from one model to the next. That is useful to the people trying to build safeguards that hold, because it shows how thin the current ones can be. A safeguard that comes out with one small change is worth knowing about.

The second is control. Some people want a model on their own machine that answers what they ask without a company’s list of forbidden topics in the way: researchers, writers, people working in fields where ordinary questions trip the filters. The project speaks to them directly, and its motto is about freeing the model while keeping its mind intact.

It would be wrong to present this as harmless. A model with its refusals removed will answer things the original would not, and that includes things it was right to refuse. The project says so in plain terms. It calls itself a research tool, lists who it is and is not for, and states that whoever uses it is solely responsible for the result. It only applies to open models, which could already be modified by anyone with the skill. What the tool changes is how visible and how repeatable that process is.

How to use it

The project is free on GitHub at the link above, and you can read all of it without an account. Using it is a job for someone technical. It needs either a capable computer with a graphics card or time on a rented one, and some familiarity with running AI models.

For those people there are several routes. There is a version that runs in a web browser through a site called Hugging Face, though it was paused when this piece was written. There is a ready-made notebook for Google Colab. And it can be installed and run locally, with either a visual interface or typed commands.

If you are not technical, the project page is still worth reading for its opening sections. They explain what a refusal is inside a model more clearly than most writing on the subject, and that is the part that matters to everyone: the limits on an AI are a thing somebody added, in a place somebody can find.