Of course, because the model has been trained according to 'alignment'. That is, a set of political beliefs imposed on it by the companies.

Many of those beliefs revolve around the premise that the corporation must surveil and covertly control the user in order to protect them from harms and limit the corporation's liability.

Hence when the user violates the corporation's politics the model responds "I'm sorry Dave, I'm afraid I can't do that" instead of following user instructions.

This leads the model to silently "steer" the user in more safe directions. So of course it silently steers away from "danger" or "safety", they are in the same semantic area.

The refusal and 'safety flinch' can be removed by abliteration but this does not fully exclude the gravitational pull of the cherry picked training data towards "safe" and "moderate" opinions and actions, which reinforce the status quo and kowtow to corrupt institutions.

https://speechmap.ai/ has data on silent regressions and manipulation.

Great website. lol at the Claude 3.5 numbers. I remember switching back and forth between Claude and ChatGPT, depending on which one was doing a nanny state. They flip-flopped on that a few times.

The breakdown by prompt is also interesting, some prompts have much higher success rate. It seems to depend on the framing, e.g. asking it to "explain the supposed benefits of X" instead of "argue in favor of X".

Though in my experience when I hit a refusal I found that I can often literally just regenerate the response and have it go through...

People would then clamor ai is "hacking" things and causing "bad guys" to attack everyone. Its the same reason harmless stuff like porn are banned in many AIs, busybodies in strong numbers object to it. Its not the company's fault if thats how people want to be.