alphacyberranger@lemmy.world to Programmer Humor@programming.devEnglish · 2 年前Its not wrong thoughlemmy.worldimagemessage-square135fedilinkarrow-up1895arrow-down183
arrow-up1812arrow-down1imageIts not wrong thoughlemmy.worldalphacyberranger@lemmy.world to Programmer Humor@programming.devEnglish · 2 年前message-square135fedilink
minus-squareamki@feddit.delinkfedilinkarrow-up9·2 年前No. Programs cannot reprogram themselves in a useful way and are very very far from it.
minus-squarelegion02@lemmy.worldlinkfedilinkarrow-up2·2 年前Eh, I’d say continuous training models are pretty close to this. Adapting to changing conditions and new input is kinda what they’re for.
minus-squareBjornir@programming.devlinkfedilinkarrow-up1·2 年前Very far from reprogramming though. The general shape of the NN doesn’t change, you won’t get a NN made to process images to suddenly process code just by training it.
minus-squareyum13241@lemm.eelinkfedilinkarrow-up1·2 年前Then how does polymorphic/self-modifying code work?
minus-squareamki@feddit.delinkfedilinkarrow-up1·2 年前It doesn’t or do you have serious applications for self-modifying code?
minus-squareyum13241@lemm.eelinkfedilinkarrow-up1·2 年前Some use it for causing millions of dollars in damage.
No. Programs cannot reprogram themselves in a useful way and are very very far from it.
Eh, I’d say continuous training models are pretty close to this. Adapting to changing conditions and new input is kinda what they’re for.
Very far from reprogramming though. The general shape of the NN doesn’t change, you won’t get a NN made to process images to suddenly process code just by training it.
Then how does polymorphic/self-modifying code work?
It doesn’t or do you have serious applications for self-modifying code?
Some use it for causing millions of dollars in damage.