Alfa@lemmy.world to ChatGPT@lemmy.world · 11 months agochatGpt is no longer Artificial Intelligence but Genuine Stupiditychat.openai.comexternal-linkmessage-square53fedilinkarrow-up1133
arrow-up1133external-linkchatGpt is no longer Artificial Intelligence but Genuine Stupiditychat.openai.comAlfa@lemmy.world to ChatGPT@lemmy.world · 11 months agomessage-square53fedilink
minus-squareSimpleDev@infosec.publinkfedilinkEnglisharrow-up12·11 months agoIdk what I’m doing wrong, thankfully it always seems to listen and work fine for me lmao
minus-squareFrostyTheDoo@lemmy.worldlinkfedilinkarrow-up19·11 months agoThe second sentence also had an s in it
minus-squareSimpleDev@infosec.publinkfedilinkEnglisharrow-up7·edit-211 months agoNow it’s broken, I guess I I don’t use it this way often enough. Interesting nonetheless! Edit - it’s very semantic, it matters if I include an uppercase “S” or not. That’s amusing. I wonder if the temperature settings adjustment would fix that or just make it even weirder.
minus-squarenieceandtows@programming.devlinkfedilinkarrow-up3·11 months agoThe original reply included both s(2) and S(10) in it
minus-squareSimpleDev@infosec.publinkfedilinkEnglisharrow-up3·edit-211 months agoBut it’s able to correct unlike what’s shown in the OP messages. Extremely semantically it seems but it clearly listens. It’s neat to see how different each person experience is. Also different tuning parameters etc…could make outputs different. That might explain why mine is seemingly a bit better at listening.
minus-squareSimpleDev@infosec.publinkfedilinkEnglisharrow-up1·11 months agoLook at the first question in the my first screenshot. It gets that question correct for “mayonnaise” lol
minus-squareHappySword@feddit.delinkfedilinkarrow-up2·11 months agoIt got it wrong when I asked it to list them
minus-squareSimpleDev@infosec.publinkfedilinkEnglisharrow-up1·edit-211 months agoI feel like ChatGPT itself probably has a fairly loose temp setting (just a hunch) and I tend to set my conversations up to be more on the strict side I imagine that’s why our results differ, it’s strange OpenAI doesn’t let ChatGPT site users or at least premium users adjust anything really yet.
Idk what I’m doing wrong, thankfully it always seems to listen and work fine for me lmao
The second sentence also had an s in it
Now it’s broken, I guess I I don’t use it this way often enough. Interesting nonetheless!
Edit - it’s very semantic, it matters if I include an uppercase “S” or not. That’s amusing.
I wonder if the temperature settings adjustment would fix that or just make it even weirder.
The original reply included both s(2) and S(10) in it
But it’s able to correct unlike what’s shown in the OP messages.
Extremely semantically it seems but it clearly listens. It’s neat to see how different each person experience is.
Also different tuning parameters etc…could make outputs different. That might explain why mine is seemingly a bit better at listening.
deleted by creator
Ask it to list the n’s
Look at the first question in the my first screenshot. It gets that question correct for “mayonnaise” lol
It got it wrong when I asked it to list them
I feel like ChatGPT itself probably has a fairly loose temp setting (just a hunch) and I tend to set my conversations up to be more on the strict side
I imagine that’s why our results differ, it’s strange OpenAI doesn’t let ChatGPT site users or at least premium users adjust anything really yet.