Arthur Besse to [email protected]English • 2 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.orgmessage-square38fedilinkarrow-up1370arrow-down110
arrow-up1360arrow-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 to [email protected]English • 2 months agomessage-square38fedilink
minus-square@[email protected]linkfedilink18•edit-22 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 hardest 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 hardest part of writing the code was already done without the LLM.