phantom-kv removes refusals by injecting an 18MB KV-cache bank

A developer released phantom-kv, which removes LLM refusals by loading a small trained bank of key/value tensors (~18MB) into the model's KV cache as context, without touching weights. The cache is hot-swappable and unloading it restores the byte-identical base model, with no refusal-direction assumption or per-layer hooks.