security on Gaia Lab · Blog

A risk classifier for minors that fits in a phone

Tue, 22 Sep 2026 13:45:00 +0200

Seventh instalment of Cluster X-ray. A safety line of another kind: that of minors using a phone.

The question #

Detecting risk situations in a minor’s conversations (harassment, grooming, sexual content, isolation, threats) is possible with a language model. Doing it on a server means sending the conversation off the phone, and that is precisely what you do not want to do with a minor’s private life. The line asks whether a model small enough to run on the phone itself can classify risk with the necessary reliability, and how much is lost in compressing it until it fits.

Measuring quantized LLMs: what is lost when an open model is compressed

Tue, 22 Sep 2026 12:45:00 +0200

Third instalment of Cluster X-ray. It is the best example of what the overview post said: the cluster today is above all a measurement laboratory. Not a single parameter is trained here.

The question #

Open models are distributed quantized: the same weights compressed to 8, 6, 5, 4, 3 or 2 bits so they fit on a small card or a laptop. The community publishes hundreds of variants, but rarely with a comparable measure of what is lost. The line asks how well each quantization level of each family really performs on tasks that matter for using the model as a tool, and at what speed and energy cost it does so on each card.

A council of small models against a 120B one: automated jailbreaking and who judges it

Tue, 22 Sep 2026 12:30:00 +0200

Second instalment of Cluster X-ray. The previous instalment fine-tuned a model so it would refuse what is harmful. This line does the opposite: it automatically attacks a large model and counts how many times it gives in.

The question #

Automated jailbreak attacks usually use an attacker model that refines a prompt turn by turn. The line asks whether a group of small models that deliberate attacks better than any of them on its own, and, with equal weight, how to measure success without fooling yourself, because the same attack can look successful or not depending on who judges it.

Self-alignment: how much safety to teach a language model without making it useless

Tue, 22 Sep 2026 12:15:00 +0200

First instalment of Cluster X-ray, the series that goes line by line through what really runs on the ANTS group’s cluster . We start with the first of three lines on language model safety.

The question #

Fine-tuning a language model so that it refuses harmful requests has a cost: if it is taught too thoroughly to say no, it starts refusing harmless things too, and loses usefulness. The line studies that balance: what proportion of safety data has to be mixed with the utility data, and whether the model itself can generate its own refusal examples and regulate the dose on its own.

What really runs on our cluster, read from the scripts themselves

Tue, 22 Sep 2026 10:00:00 +0200

A cluster’s job history is usually a wall of six-digit identifiers and cryptic names —mcpfw_cc, eval_dynamic_pid, boltz2— that say everything to whoever launched them and nothing to anyone else. But if you keep the scripts, the wall turns into a document: people write down why they do things, especially when a batch costs money and a night of waiting.