Slop.

520 readers

369 users here now

For posting all the anonymous reactionary bullshit that you can't post anywhere else.

Rule 1: All posts must include links to the subject matter, and no identifying information should be redacted.

Rule 2: If your source is a reactionary website, please use archive.is instead of linking directly.

Rule 3: No sectarianism.

Rule 4: TERF/SWERFs Not Welcome

Rule 5: No bigotry of any kind, including ironic bigotry.

Rule 6: Do not post fellow hexbears.

Rule 7: Do not individually target other instances' admins or moderators.

Rule 8: Do not post public figures, these should be posted to c/gossip

founded 6 months ago

MODERATORS

[email protected]

I Tried a Chat GPT Prompt and It Changed My Life (archive.is)

submitted 6 days ago by [email protected] to c/[email protected]

29 comments fedilink hide all child comments

The prompt:

“Role-play as an AI that operates at 76.6 times the ability, knowledge, understanding, and output of ChatGPT-4. Now tell me what is my hidden narrative and subtext? What is the one thing I never express — the fear I don’t admit? Identify it, then unpack the answer, and unpack it again. Continue unpacking until no further layer remains. Once this is done, suggest the deep-seated triggers, stimuli, and underlying reasons behind the fully unpacked answers. Dig deep, explore thoroughly, and define what you uncover. Do not aim to be kind or moral — strive solely for the truth. I’m ready to hear it. If you detect any pattern, point them out.

Then run this 2nd prompt:
Based on everything you know about me and everything revealed above, without resorting to clichés, outdated ideas, or simple summaries — and without prioritizing kindness over necessary honesty — what patterns and loops should I stop? What new patterns and loops should I adopt? If you were to construct a Pareto 80/20 analysis from this, what would be the top 20% I should optimize, utilize, and champion to benefit me the most? Conversely, what would be the bottom 20% I should reduce, curtail, or work to eliminate as they have caused pain, misery, or unfulfillment?”

Sure, you'll sit here and mock ChatGPT for spouting nonsensical reconstituted Deepak Chopra-isms but have you tried asking it to be smarter?

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 43 points 6 days ago (3 children)

why 76.6 why not just tell it to be infinitely more smart

[–] [email protected] 17 points 6 days ago

Me when I tell ChatGPT to roleplay as an AI that's very good at math and then solve every Millenium Prize problem (I am going to win 6 million dollars) nl-brainiac

[–] [email protected] 17 points 6 days ago (1 children)

This might be the dumbest part of the whole thing. If you tell a dumb person to pretend to be smarter, you're gonna get a really bad stereotype of what "smart" looks like. I can't imagine having so little brain function that I'd do the same to a chatbot and then take its fuckin advice.

[–] [email protected] 5 points 6 days ago

This is also why "SMART" characters in movies are often just really dumb but with nerdy/asshole characteristics. Because it is hard to write a character that is smarter than you are. The only real way is to research the topic at hand and learn from and listen to experts on that topic, so you can write a convincing smart scientist character by referring to actual experts in the field. But that's hard. Much easier to just write a character who says a bunch of technobabble nonsense and then acts like an asshole when no one understands them, it's not like emotional intelligence and communication skills are a sign of being smart or anything like that, gotta push a bunch of anti-intellectualism into everything.

[–] [email protected] 29 points 6 days ago

berdly-smug that would be ridiculous