[vessenes]

Not just this, but I’ve been thinking that naming things with aggressively strong connotations might help Claude get out of ‘nice/helpful’ mode. “You are the Deacon, grrrrr”. So there might be actually be a bit of effectiveness added by naming an agent appropriately. I offer no opinion on the word polecats.

[ivankra]

Maybe helps the LLM, but at the cost of confusing humans. It would've been better left as an internal implementation detail. I've got better things to keep in my head that remembering wtf deacon is, etc.

[3dsnano]

yes, totally. AI-luddites see this as whimsy, but it's actually wizard-level power of abstractions and context ascension. if u know u know