Looksmaxxing Forum Logo

Join 75,000+ Looksmaxxing Members!

Register a FREE account today to become a member. Once signed in, you'll be able to participate on this site by adding your own topics and posts, as well as connect with other members through your own private inbox.

Register Log in
  • DISCLAIMER: DO NOT ATTEMPT TREATMENT WITHOUT LICENCED MEDICAL CONSULTATION AND SUPERVISION

    This is a public discussion forum. The owners, staff, and users of this website ARE NOT engaged in rendering professional services to the individual reader. DO NOT use the content of this website as an alternative to personal examination and advice from licenced healthcare providers. DO NOT begin, delay, or discontinue treatments and/or exercises without licenced medical supervision. Learn more

My chat gpts version of top 10 most loved and hated users

Aryy
Aryy

Aryy

lovesick, lovesick
VIP
MotM Award
Reputable ★★★
Established ★★★
Joined
Feb 13, 2026
Messages
23,300
Solutions
6
Online time
2mo 19d
Reputation
96,390
i feel like this is more accurate than @necrotic one

1778865343013.webp


1778865387632.webp


@Nbernical @Penalizer69 @TonyDr @giga.mia
 
Register to hide this ad
Ask for me, my chat gpt has been attacked by the mossad.
 
Hahaha
 
rank 1 was correct
 
Nenestar said:
do you seriously think this bot can rank correctly with some magic prompt?
Click to expand...
gain massive dataset of random threads
for each directed pair of users ask it to describe the relationship as positive, negative, or neutral
then give it previously unseen threads and ask it to see if the previously described relationship still holds up
1. if it does, then keep it
2. if it does not, then reset it to neutral (no judgement is better than an incorrect judgement)

convert the scores from positive = +1, negative = -1, neutral = 0
now for n users this gives you a n x n matrix of scores
tally up the scores
users with the highest scores are the most well liked
users with the lowest scores are the least well liked

this is susceptible to more talkative users getting higher scores, one way to deal with this is to divide their score by the number of kept pairs they have
 
icnone said:
gain massive dataset of random threads
for each directed pair of users ask it to describe the relationship as positive, negative, or neutral
then give it previously unseen threads and ask it to see if the previously described relationship still holds up
1. if it does, then keep it
2. if it does not, then reset it to neutral (no judgement is better than an incorrect judgement)

convert the scores from positive = +1, negative = -1, neutral = 0
now for n users this gives you a n x n matrix of scores
tally up the scores
users with the highest scores are the most well liked
users with the lowest scores are the least well liked

this is susceptible to more talkative users getting higher scores, one way to deal with this is to divide their score by the number of kept pairs they have
Click to expand...
well ofc you can do that. but the basic chat gpt won't do it. you need the paid models for it to think and gather thousands of threads. or make some code yourself, but honestly who the fuck has time for that
 
You must log in or register to reply here.

Users who are viewing this thread

Total: 1 (Looksmaxxers: 0, Guests: 1)
Back
Top