"And these are usually the people who don't run extensive fuzzing and test suites" yikes sounds bad
[dead]
oh, in no way i am claiming 'magical' LLMs don't write buggy code and that there isn't some tradeoff in using them. with llm also you have pretty much take care and make it write secure. Yes landscape changed massively.…
with AI this problem becomes more acute, now the MOAT is the brain and the logic code is just disposable stuff now i guess
everybody new Vulnerability makes me think how we are not so good a writing secure code?.
"And these are usually the people who don't run extensive fuzzing and test suites" yikes sounds bad
[dead]
oh, in no way i am claiming 'magical' LLMs don't write buggy code and that there isn't some tradeoff in using them. with llm also you have pretty much take care and make it write secure. Yes landscape changed massively.…
with AI this problem becomes more acute, now the MOAT is the brain and the logic code is just disposable stuff now i guess
everybody new Vulnerability makes me think how we are not so good a writing secure code?.