Canonical event

AE Studio and Anthropic publish research on GRAM modular pretraining for capability isolation

On 8 July 2026, AE Studio researchers collaborating with Anthropic publicly described Gradient Routed Auxiliary Modules (GRAM) for isolating selected learned knowledge in removable modules. They reported controlled experiments on synthetic text and dual-use-domain datasets across model sizes from 50M to 5B parameters. This preliminary study did not demonstrate robust capability removal at frontier-model scale and explicitly said the technique had not been applied to Anthropic production models; provider-reported results are not independent replication.