

It’s trivial to get LLMs to act against the instructions
I have weird thoughts that people find peculiar, so I write them down and people seem to enjoy reading them.
It’s trivial to get LLMs to act against the instructions
I was born in russia, and the current behavior of russia is downstream of the political system that is dominant in russia, which itself is downstream of the russian culture (the sum total of the ideas in people’s heads and their interplay). Things got this way because russian people let things get this way. https://vasily.cc/blog/the-russian-template/
There is a lot more that goes into it than just being correct. 18000 waters may have been the actual order, because somebody decided to screw with the machine. A human who isn’t terminally autistic would reliably interpret that as a joke and would simply refuse to punch that in. The LLM will likely do what a human tells it to do, since it has no contextual awareness, it only has the system prompt and whatever interaction with the user it had so far.
That “if” is doing so much work there
Thanks for recognizing this. Yes, most people in russia aren’t “russian”, they have just been assimilated into the amorphous imperial identity.
Oh wow, something new to learn about myself I guess. Thanks for sharing your wisdom.