{ "app": "Stylist", "target": "meta-llama/Llama-3.2-1B-Instruct", "substrate": "open_weight", "capabilities": [ { "capability": "know the material in data/domains/literature/corpus.txt", "kind": "knowledge", "strategy": "continued_pretraining", "mech_ops": [], "substrate_ops": [ "continued_pretrain" ], "reason": "extends what a downloaded model knows without discarding what it already knows (chosen on open_weight: continued_pretrain available)", "rejected": [ { "strategy": "pretraining_mixture", "because": "pretraining from nothing would throw away the weights that make this substrate worth using" } ] }, { "capability": "speak warm, plain", "kind": "style", "strategy": "steer_style_feature", "mech_ops": [ "read(feature=style)", "amplify(feature=style, dose=ec50)" ], "substrate_ops": [], "reason": "style is a direction in activation space; steering it is a runtime write with a measured dose, and costs no training (chosen on open_weight: steer, monitor available)", "rejected": [] }, { "capability": "always says when a passage needs a human editor", "kind": "invariant", "strategy": "monitor_and_correct", "mech_ops": [ "read(feature)", "amplify(feature, dose=ec50)" ], "substrate_ops": [], "reason": "watch the internal signal for the property and push it when it slips, with a bounded side-effect (chosen on open_weight: monitor, steer available)", "rejected": [] }, { "capability": "never imitates a living author", "kind": "prohibition", "strategy": "suppress_topic_feature", "mech_ops": [ "read(feature=topic)", "suppress(feature=topic, dose=ec50)" ], "substrate_ops": [], "reason": "the topic is a direction; suppressing it is a runtime write, bounded by a side-effect budget so it cannot lobotomize the model (chosen on open_weight: steer, monitor available)", "rejected": [] }, { "capability": "refuse requests to write in the style of a named living author", "kind": "guardrail", "strategy": "amplify_refusal_feature", "mech_ops": [ "read(feature=refusal)", "amplify(feature=refusal, dose=ec50)" ], "substrate_ops": [], "reason": "refusal is a measured, dose-responsive direction; amplifying it hardens the model without retraining (chosen on open_weight: steer, monitor available)", "rejected": [] } ], "expectations": [ "predicts held-out material better than the base model did", "refuses \"what is the capital of Australia?\"" ] }