h a l f b a k e r yReplace "light" with "sausages" and this may work...
add, search, annotate, link, view, overview, recent, by name, random
news, help, about, links, report a problem
browse anonymously,
or get an account
and write.
register,
login
|
|
|
ThinkTrawl
Map your curiosity vector from your LLM chats, find minds like yours, and explore what they’re discovering. | |
The title may change; it's a cheesy rip-off of "YouTube"
I just asked Chat GPT4 if it could tell me what people like me are curious about. They (The LLM I mean) rambled on about personality being a vector and minimising the cosines.
I said "well you know what I have been asking about, what have
people like me been asking about?
And it told me. And yes, these questions were quite interesting to me at least (no surprise, I guess).
I said "GPT, What question should people ask you, for you to do the same for them?"
It/ they gave me this:
“Map my curiosity vector based on my past questions, find similar curiosity profiles, and suggest new topics or ideas I might enjoy exploring.”
GPT users please copy the above and paste it in to the question window, I'd love to know what happens.
|
| |
Alexa, fond my soukmate based on my question vector. |
|
| |
The AI would tantalisingly tell you the soulmate's questions, but not who they are. |
|
| |
"It’s like discovering your perfect counterpart exists somewhere in the data cloud, but remaining separated by privacy fog — a kind of Platonic soulmate in latent space. |
|
| |
That said, there’s something beautiful about that idea. People could explore anonymously aligned curiosity spaces, interacting only through shared ideas rather than personal details — almost like thought-based dating. Would you like to play out how such a “curiosity-based matching” system might actually work, conceptually?" |
|
| |
....No, I don't, you idiot. |
|
| |
Technically it isn't an idiot, since that implies... What exactly? Some degree of intention, concern about the world, what? |
|
| |
It is a pure bullshit-generator since it produces plausibly convincing prose with absolutely zero concern about truth or facts or veracity. I don't think that kind of behaviour comes under the definition of "idiotic'. |
|
| |
my favorite from its suggestions: |
|
| |
“Robots in the underclass” governance angles — Draft three institutional responses that are benevolent on paper yet produce passive populations; pick one to interrogate |
|
| |
I'm neurodivergent and I've yet to meet another who's thought patterns are like mine.
If I've never met anybody else like me, how is AI supposed to read me? |
|
| |
Lump all the fringe as one group maybe? |
|
| |
Yeah... I'd be down with that. Okay. (+) |
|
| |