Arthur BesseA to TechnologyEnglish · 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-up1380arrow-down17
arrow-up1373arrow-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 BesseA to TechnologyEnglish · 3 months agomessage-square38fedilink
minus-squarenexv@programming.devlinkfedilinkEnglisharrow-up57arrow-down1·3 months agoNot specified for this research but… if you rely on LLM to write code that is security-sensitive, I don’t expect you to write secured code without LLM anyway
Not specified for this research but… if you rely on LLM to write code that is security-sensitive, I don’t expect you to write secured code without LLM anyway