Scarronline@lemmy.world to Mildly Infuriating@lemmy.worldEnglish · 1 year agoOnline datinglemmy.worldimagemessage-square426fedilinkarrow-up12.77Karrow-down173cross-posted to: datingredflags@lemmy.tf
arrow-up12.7Karrow-down1imageOnline datinglemmy.worldScarronline@lemmy.world to Mildly Infuriating@lemmy.worldEnglish · 1 year agomessage-square426fedilinkcross-posted to: datingredflags@lemmy.tf
minus-squaretweeks@feddit.nllinkfedilinkEnglisharrow-up5·1 year agoMight I ask if you were using Chat-GPT 3 or 4? I had this as well, got send into circles for hours, with 3. Then I used 4. Only two bloody messages back and forth and I got my solution.
minus-squareWololo@lemmy.worldlinkfedilinkEnglisharrow-up2·1 year agoIf I remember correctly it should have been gpt-4, of course, there is always a chance it was 3.5 Since then I’ve learned much better ways to kind of manipulate it into answering my questions more precisely, and that seems to do the trick
minus-squaretweeks@feddit.nllinkfedilinkEnglisharrow-up1·1 year agoOne might wonder who is training who.
minus-squaremusic@lemmy.worldlinkfedilinkEnglisharrow-up1·1 year agoIs 4 trained on newer data than Sept 2021?
minus-squaretweeks@feddit.nllinkfedilinkEnglisharrow-up1·1 year agoJust a little bit, the main set is just September 2021 but some specific additional data (and other modifications) has been used to further improve the model.
Might I ask if you were using Chat-GPT 3 or 4? I had this as well, got send into circles for hours, with 3. Then I used 4.
Only two bloody messages back and forth and I got my solution.
If I remember correctly it should have been gpt-4, of course, there is always a chance it was 3.5
Since then I’ve learned much better ways to kind of manipulate it into answering my questions more precisely, and that seems to do the trick
One might wonder who is training who.
Is 4 trained on newer data than Sept 2021?
Yes
Just a little bit, the main set is just September 2021 but some specific additional data (and other modifications) has been used to further improve the model.