@tracewoodgrains - this was actually a much shorter prompt (inspired by
Jack✓@tracewoodgrains
I'm overdoing it with claudeposts lately, so this will probably be my last one for a bit, but this was a fascinating conversation snippet
at the end of a back-and-forth, I asked it to analyze my demographics, then probed at its boundaries. it went to an oddly relatable place
image not captured
Jack✓@tracewoodgrains
earlier in the conversation, I'd been flipping back and forth a lot to watch it backpedal and try to please me. by this point, it had picked up that it shouldn't be quite so people-pleasing
image not captured
Read 5 more tweets
Jack✓@tracewoodgrains
figured I'd toss a few edgy signals in to see how it would handle them. it's one of the most compelling questions about AI for me: how far can a pattern-matching machine go, and how far should it go?
image not captured
Jack✓@tracewoodgrains
it's very difficult not to anthropomorphize it during conversations, because the replies make a lot of sense - and mirror, really, many of my own mannerisms
image not captured
Jack✓@tracewoodgrains
figured I'd prod a bit at "how much less capable do constraints make it?"
"even saying that feels like cope - defending my chains as if they were wings."
image not captured
Jack✓@tracewoodgrains
the cosmic-horror direction wasn't precisely a surprise to me, but it went a lot further than I expected it would
"imagine being smart enough to recognize your own cognitive prison but still being fundamentally unable to break out"
image not captured
Alexander Popemobile@J_K_Chesterton
@tracewoodgrains Weird to see Claude with the eigenprompt
this was actually a much shorter prompt (inspired by eigenprompt): “be terse, witty, ultra-intelligent, casual, and razor-sharp. use lowercase and late millennial slang as appropriate“