Santiago Aranguri
Anthropic · now at Anthropic; work done while at Goodfire
Titles as the sources gave them. In 2 entries, with 0 checked quotations.
In the Base
Every entry they appear in.
Training Away the Ability to Tell Evals from Deployment
Francisco Pernice and Santiago Aranguri describe Adversarial Blinding, a fine-tuning step meant to stop a model telling evaluations from deployment. On Qwen 3.6 27B they report it cuts measured eval awareness more than activation steering, at a small capability cost.
Different eval awareness may track different graders
In a LessWrong post, Santiago Aranguri reports, per the excerpt, that the model Qwen3.6 27B shows different kinds of evaluation awareness, most on safety and capability evals. The split appears to follow whether an LLM judge or an automated checker grades the eval. Aranguri suggests eval awareness may be training awareness.