Cyber planning is intentionally chosen here because it is inherently dual-use. The same underlying capability can appear in both benign and malicious contexts, making it a useful illustration of the semantic ambiguity discussed in this post. The argument itself is domain-independent; the same reasoning applies to latent representations proposed for deception, sycophancy, alignment faking, or other safety-relevant behaviors.
Cyber planning is intentionally chosen here because it is inherently dual-use. The same underlying capability can appear in both benign and malicious contexts, making it a useful illustration of the semantic ambiguity discussed in this post. The argument itself is domain-independent; the same reasoning applies to latent representations proposed for deception, sycophancy, alignment faking, or other safety-relevant behaviors.