🍹Early to RISA 🧉@sh.itjust.worksM to Greentext@sh.itjust.works · 17 hours agoAnon cheats through collegesh.itjust.worksimagemessage-square125fedilinkarrow-up1382arrow-down111
arrow-up1371arrow-down1imageAnon cheats through collegesh.itjust.works🍹Early to RISA 🧉@sh.itjust.worksM to Greentext@sh.itjust.works · 17 hours agomessage-square125fedilink
minus-squareEheran@lemmy.worldlinkfedilinkarrow-up3·3 hours agoSince 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-up1·51 minutes agoIf 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
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