Arthur Besse@lemmy.ml to Technology@lemmy.mlEnglish · 3 months ago"participants who had access to an AI assistant wrote significantly less secure code" and "were also more likely to believe they wrote secure code" - 2023 Stanford University study published at CCS23arxiv.orgexternal-linkmessage-square38fedilinkarrow-up1379arrow-down17
arrow-up1372arrow-down1external-link"participants who had access to an AI assistant wrote significantly less secure code" and "were also more likely to believe they wrote secure code" - 2023 Stanford University study published at CCS23arxiv.orgArthur Besse@lemmy.ml to Technology@lemmy.mlEnglish · 3 months agomessage-square38fedilink
minus-squareNauticalNoodle@lemmy.mllinkfedilinkarrow-up18·edit-23 months agoIt seems to me that if one can adequately explain the function of their pseudocode in adequate detail for an LLM to turn it into a functional and reliable program, then the hard part of writing the code was already done without the LLM.
It seems to me that if one can adequately explain the function of their pseudocode in adequate detail for an LLM to turn it into a functional and reliable program, then the hard part of writing the code was already done without the LLM.