Illustration, AI-generated from the story text. Tap a panel to enlarge.

Britain tests whether removing training data can limit biological model capabilities

The AI Security Institute published experiments on filtering pretraining data for an open-weight protein model. In the tested model family, filtering selectively reduced targeted viral capabilities without the same decline in adjacent capabilities.

The researchers also found that subsequent fine-tuning could recover capabilities. That limits the protection available from a training-data filter once weights can be modified. The evidence concerns a particular experimental model family; it does not establish either universal safety or universal failure across biological AI. SourcesA

Sources

• ABritain tests whether removing training data can limit biological model capabilitiesaisi.gov.uk

This story ran in the Morning Brief of October 27th 2026.