logoalt Hacker News

hparadiz • today at 5:56 PM • 2 replies • view on HN

This is true for human written code too. This is why in the future all written code MUST be run through an internal security sweep before being given to your harness for writing. That's just basic due diligence at this point.


Replies

vbezhenar • today at 6:35 PM

As long as model providers deny access to security-capable models, it can't be basic diligence.

➕ show 1 reply
catlifeonmars • today at 6:18 PM

Yes but LLMs famously produce vastly more code than humans. My hot take: LLMs will produce more insecure code than they can catch, and will also find ways to smuggle insecure code to avoid extra work.