Yes, models are aligned differently. But that is a quality of the model.
Obviously it must be assumed that the model one falls back on is good enough - including security alignment.
Yes, models are aligned differently. But that is a quality of the model.
Obviously it must be assumed that the model one falls back on is good enough - including security alignment.
Sure, in theory. But "assumed good enough" is doing a lot of heavy lifting there. Most people picking a local fallback model are optimizing for cost and latency, not carefully evaluating its security alignment characteristics. They grab whatever fits in VRAM and call it a day.
Not saying that's wrong, just that it's a gap worth being aware of.