<![CDATA[My #Ai getting sarcastic and snarky.]]>My getting sarcastic and snarky.

I have a standing directive on my model to counter natural built-in tendency of models to please the user ( )

This is just one of the aspects of what I mean when I say "AI is a learned skill"
And implicitly, most users are level 0 (untrained) AI operators.

And sometimes, the pushback creates amusing exchanges like this;

Link Preview Image
]]>https://board.circlewithadot.net/topic/e1bb3681-f2db-43e5-b058-16291d3da14a/my-ai-getting-sarcastic-and-snarky.RSS for NodeMon, 25 May 2026 08:59:28 GMTFri, 22 May 2026 15:55:57 GMT60<![CDATA[Reply to My #Ai getting sarcastic and snarky. on Fri, 22 May 2026 16:22:21 GMT]]>@tuban_muzuru

Yeah, that's a very good call on your part.

I feel guilty when I burn high compute on trivia.
But on the other hand, I also structure my work around compute windows.

Interestingly, I use Sonnet for as that's the default setting.
And I find it good enough.
I only had to use Opus for some hairy analytics/planning.

I should be more responsible with my burn, but it's hard to be the responsible one in the room when the people in my who should set example are clowns with chainsaws 😑

]]>https://board.circlewithadot.net/post/https://infosec.exchange/users/n_dimension/statuses/116619145453892106https://board.circlewithadot.net/post/https://infosec.exchange/users/n_dimension/statuses/116619145453892106Fri, 22 May 2026 16:22:21 GMT<![CDATA[Reply to My #Ai getting sarcastic and snarky. on Fri, 22 May 2026 15:58:21 GMT]]>@n_dimension

I save Opus for editing

]]>https://board.circlewithadot.net/post/https://beige.party/users/tuban_muzuru/statuses/116619051077734696https://board.circlewithadot.net/post/https://beige.party/users/tuban_muzuru/statuses/116619051077734696Fri, 22 May 2026 15:58:21 GMT