🍹Early to RISA 🧉@sh.itjust.worksM to Greentext@sh.itjust.works · 3 天前Anon cheats through collegesh.itjust.worksimagemessage-square185fedilinkarrow-up1529arrow-down118
arrow-up1511arrow-down1imageAnon cheats through collegesh.itjust.works🍹Early to RISA 🧉@sh.itjust.worksM to Greentext@sh.itjust.works · 3 天前message-square185fedilink
minus-squareSoftestSapphic@lemmy.worldlinkfedilinkarrow-up6·edit-22 天前If you copy and paste from ChatGPT your code won’t compile. You need to know what the peices of code do and how to peice them together to make it work. Which is kind of impossible to do without understanding it
minus-squareEheran@lemmy.worldlinkfedilinkarrow-up3·2 天前Since version 4 it has no problem generating working code. The question is how complex the code can get etc. But currently with o1 (o3 mini perhaps a bit less) a dozen functions with 1000 lines of code are really possible without a flaw.
minus-squareSoftestSapphic@lemmy.worldlinkfedilinkarrow-up1·2 天前If I tell ChatGPT “write me a program in python that does X, Y, and Z” it will not output code that can be compiled or ran without editing
If you copy and paste from ChatGPT your code won’t compile.
You need to know what the peices of code do and how to peice them together to make it work.
Which is kind of impossible to do without understanding it
Since version 4 it has no problem generating working code. The question is how complex the code can get etc. But currently with o1 (o3 mini perhaps a bit less) a dozen functions with 1000 lines of code are really possible without a flaw.
If I tell ChatGPT “write me a program in python that does X, Y, and Z” it will not output code that can be compiled or ran without editing